© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    拓远, 玉山, 蹴鞠, 平江路, 天气真好, 煎饼, 明里

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    S
    2.52
    M
    2.25
    т
    2.14
    νε
    2.11
    in
    2.08
    al
    1.98
    le
    1.94
    m
    1.91
    H
    1.89
    is
    1.88
    POSITIVE LOGITS
     vínculos
    2.50
     ocasião
    2.40
     medicamento
    2.35
     antigos
    2.34
     entrar
    2.25
     ofrecer
    2.25
     estadounidense
    2.23
     propietario
    2.22
     exponentes
    2.22
     longitudine
    2.21
    Activations Density 0.025%

    No Known Activations