© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2535
    Prev
    Next
    INDEX
    Explanations

    responsible for how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ណ្ឌ
    1.03
     czter
    1.03
    ະລ
    0.94
     thre
    0.94
    ContextHeader
    0.94
    पर्यंत
    0.93
    τρέ
    0.93
    :${
    0.93
    footed
    0.93
     bốn
    0.92
    POSITIVE LOGITS
    /
    1.00
    #
    0.91
    無く
    0.90
    //
    0.89
     अजय
    0.87
    Stay
    0.87
     беременности
    0.85
     stay
    0.84
     Stay
    0.83
     iyo
    0.81
    Activations Density 0.179%

    No Known Activations