© 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. 2450
    Prev
    Next
    INDEX
    Explanations

    producing model answers

    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
    Не
    1.97
     Не
    1.81
    Ва
    1.71
     не
    1.67
     НЕ
    1.65
     핵심
    1.61
    ‪
    1.60
     ไม่
    1.56
    Без
    1.56
    Ре
    1.54
    POSITIVE LOGITS
     wanneer
    1.09
     bus
    1.04
     campione
    1.03
     indien
    1.03
     m
    1.01
     firm
    0.99
     sao
    0.99
     sai
    0.95
     welches
    0.94
     Ekim
    0.93
    Activations Density 0.015%

    No Known Activations