© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2390
    Prev
    Next
    INDEX
    Explanations

    paraphrases and rewrites

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

    The neuron fires most strongly on less common, content-bearing words—that is, rarer vocabulary tokens rather than high-frequency function words.

    oai_token-act-pair · o4-miniTriggered 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
     pâ
    0.77
    re
    0.76
    d
    0.72
    ied
    0.71
    vpc
    0.69
     ample
    0.68
     dites
    0.67
     e
    0.66
    ignation
    0.66
    네
    0.66
    POSITIVE LOGITS
     stallions
    0.86
     disminución
    0.84
     llegan
    0.82
     употреб
    0.82
     compuestos
    0.82
    ς
    0.80
    ൦
    0.80
    ゅう
    0.79
    위원
    0.79
    ات
    0.79
    Activations Density 0.000%

    No Known Activations