© 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. 12631
    Prev
    Next
    INDEX
    Explanations

    `:` `as` `your` `narrative` `of` `number`

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

    The neuron fires strongly on content-bearing words—especially nouns and salient adjectives—while ignoring most 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
    in
    1.13
    em
    0.84
    op
    0.83
    classified
    0.82
    en
    0.79
    is
    0.77
    xt
    0.73
    v
    0.72
    on
    0.72
    ub
    0.70
    POSITIVE LOGITS
     restrooms
    0.86
     restroom
    0.84
     décès
    0.79
     ceremonies
    0.79
     contingencies
    0.78
     accidents
    0.76
     légumes
    0.76
     symptômes
    0.75
     জানিয়ে
    0.75
     allege
    0.75
    Activations Density 0.000%

    No Known Activations