© 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. 2158
    Prev
    Next
    INDEX
    Explanations

    comparative and qualitative descriptors

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

    The neuron fires most strongly on very high‐frequency function words—common pronouns, auxiliaries, articles, and similar “grammatical glue” tokens.

    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
    .
    0.99
    -
    0.96
    ↵↵
    0.95
     -
    0.88
    /
    0.86
    :
    0.84
    ↵
    0.84
    ;
    0.79
     =
    0.79
     andre
    0.79
    POSITIVE LOGITS
     människor
    0.80
     ಜನರು
    0.79
     Menschen
    0.76
     മനുഷ്യ
    0.75
     মানুষের
    0.73
     انسان
    0.71
     લોકો
    0.71
    មនុស្ស
    0.71
     peuple
    0.70
    abhavena
    0.70
    Activations Density 2.111%

    No Known Activations