© 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. 13217
    Prev
    Next
    INDEX
    Explanations

    sellers, Weaver, observer

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

    The neuron fires strongly on plural agent nouns denoting people or organizations who supply, produce, or perform services (e.g. “suppliers,” “providers,” “directors,” “producers,” “filmmakers,” etc.).

    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
    考え
    0.80
    ぉ
    0.71
    きて
    0.71
     tratamento
    0.70
    govor
    0.70
    ्तीय
    0.69
    ライダー
    0.69
    ्स
    0.69
    ří
    0.69
     ownership
    0.69
    POSITIVE LOGITS
     extraordinaire
    1.30
     Beware
    0.69
    នៃ
    0.68
     beware
    0.68
    /
    0.68
     cum
    0.65
    වර
    0.64
    responsible
    0.63
    et
    0.61
    ‍♂️
    0.61
    Activations Density 0.554%

    No Known Activations