© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10077
    Prev
    Next
    INDEX
    Explanations

    What do you

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

    This neuron highlights the word “do” when it appears in a “how do …” question.

    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
     there
    0.89
     และ
    0.71
    there
    0.68
     Và
    0.66
     మరియు
    0.63
     she
    0.61
     和
    0.61
    soever
    0.61
    とその
    0.61
     theres
    0.60
    POSITIVE LOGITS
    一本
    0.62
    없는
    0.60
     toppers
    0.55
     OTHERWISE
    0.54
     такую
    0.54
    such
    0.53
    IGR
    0.52
    డయ
    0.52
    덴
    0.52
    Analysts
    0.52
    Activations Density 0.076%

    No Known Activations