© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3415
    Prev
    Next
    INDEX
    Explanations

    parenthetical definitions of coffee or signalling

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

    The neuron fires on semantically “heavy” content words (not function words), essentially picking out the key nouns and topic-bearing terms in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    Pentru
    0.87
    Untuk
    0.75
     هيكون
    0.73
     ہے۔
    0.72
    Для
    0.71
    %).
    0.71
     جائے۔
    0.69
    Until
    0.68
    %.
    0.67
    %。
    0.67
    POSITIVE LOGITS
     (
    0.81
     (“
    0.80
     (!)
    0.80
     (‘
    0.77
     ()
    0.75
     plus
    0.74
     extraordinaire
    0.72
     (?)
    0.71
     („
    0.71
     of
    0.69
    Activations Density 0.555%

    No Known Activations