© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12198
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on uncommon, content‐bearing nouns (e.g. “ingredients,” “software,” “options,” “test,” “effect”) rather than on 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_31_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
     Saturdays
    0.66
     Mondays
    0.61
     IOError
    0.56
     Fridays
    0.54
     Thursdays
    0.53
    ဋ
    0.52
     launchers
    0.52
    ﺮ
    0.51
     দরকার
    0.50
     NSError
    0.50
    POSITIVE LOGITS
    prize
    0.56
     rate
    0.55
     örnek
    0.54
     aos
    0.53
     yeni
    0.53
    శి
    0.53
    trial
    0.52
     있었
    0.52
     Sending
    0.52
     eş
    0.52
    Activations Density 0.000%

    No Known Activations