© 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. 91426
    Prev
    Next
    INDEX
    Explanations

    Soviet Union

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

    claims or specific information

    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
    ３
    0.56
    进口
    0.46
    خير
    0.45
    Substituting
    0.45
    ５
    0.44
    ۳
    0.44
    Navigation
    0.44
    ７
    0.43
     CALL
    0.43
    Indexing
    0.42
    POSITIVE LOGITS
    int
    0.44
     intrac
    0.43
     flint
    0.43
     віднов
    0.43
     archae
    0.43
    ologische
    0.43
     interwoven
    0.42
     thom
    0.42
    iczne
    0.41
     foal
    0.41
    Activations Density 0.000%

    No Known Activations