© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17204
    Prev
    Next
    INDEX
    Explanations

    list entries or names

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

    friend, family, professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    /
    0.35
     pioneered
    0.34
     (
    0.33
     de
    0.31
     Scientology
    0.31
    远离
    0.30
     Surgical
    0.29
     sculptor
    0.29
     Zeiten
    0.29
     Ausdruck
    0.29
    POSITIVE LOGITS
    を入
    0.37
    𒌋
    0.35
    入場
    0.34
     간단
    0.33
    簡単な
    0.33
    。</
    0.32
     확인
    0.32
    玉
    0.32
    が入
    0.31
    繁忙時間服務
    0.31
    Activations Density 0.001%

    No Known Activations