© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14259
    Prev
    Next
    INDEX
    Explanations

    AI image generators, libraries, thresholds

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on uncommon or out‐of‐vocabulary tokens—rare words, acronyms, and unusual strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    colons that introduce direct speech, quotes, or listed information in formal or structured text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    parenthetical or appositive insertions and other separator-style constructions (like parentheses, slashes, dashes, and colons) that introduce asides or clarifications.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teorías
    0.88
     baseApiPath
    0.87
     reflectivity
    0.84
     investigaciones
    0.80
     strony
    0.80
     signification
    0.77
     ہمارے
    0.77
    应用的
    0.77
     inventories
    0.77
     decimos
    0.76
    POSITIVE LOGITS
    ^(
    0.71
    a
    0.70
     Adapted
    0.69
    adapted
    0.68
    0.65
     Lyrics
    0.63
     erhielt
    0.63
     Asoci
    0.61
    ре
    0.60
    igung
    0.60
    Activations Density 0.000%

    No Known Activations