© 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. 169080
    Prev
    Next
    INDEX
    Explanations

    energy, language, or government information

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

    in minutes, response, covering

    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
    ಸೆ
    0.48
    SU
    0.45
    arrière
    0.45
    বেশী
    0.44
    REF
    0.44
    ice
    0.43
    ＰＥ
    0.43
    ν
    0.43
    VN
    0.43
    irane
    0.43
    POSITIVE LOGITS
    лод
    0.47
     localVarHTTP
    0.46
     تقدر
    0.43
     عندي
    0.42
     loaders
    0.42
     Engage
    0.42
     semper
    0.42
     MaterialApp
    0.42
    etchup
    0.42
     Normalized
    0.42
    Activations Density 0.001%

    No Known Activations