© 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. 4061
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    The neuron primarily detects occurrences of proper names or branded product/company identifiers.

    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
    it
    0.80
     Bitte
    0.75
    dome
    0.75
    iatica
    0.75
    نی
    0.74
    daten
    0.73
    cornerRadius
    0.73
    ֑
    0.73
    dari
    0.73
    dine
    0.73
    POSITIVE LOGITS
     corset
    0.74
     Fleurs
    0.68
     U
    0.68
     rein
    0.68
     хле
    0.68
     tall
    0.67
     ensembles
    0.67
     tempo
    0.66
     произво
    0.66
     reins
    0.66
    Activations Density 0.005%

    No Known Activations