© 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. 41513
    Prev
    Next
    INDEX
    Explanations

    .

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

    explains creation and sensitive topics

    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
    曛
    0.51
     січня
    0.49
     terlalu
    0.48
     ಹೆಚ್ಚಿನ
    0.48
     Tujuan
    0.47
     Рассмотрим
    0.47
     Сі
    0.47
    वाहिक
    0.46
     Дан
    0.44
    过于
    0.44
    POSITIVE LOGITS
    P
    0.51
     as
    0.50
    __
    0.49
    institut
    0.46
     RAF
    0.46
    I
    0.44
    draft
    0.43
    爣
    0.43
    -%
    0.43
     undergraduate
    0.43
    Activations Density 0.000%

    No Known Activations