© 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. 15530
    Prev
    Next
    INDEX
    Explanations

    listed below

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

    zeros

    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
     verschill
    0.50
    த்துடன்
    0.49
     بیاکتنې
    0.47
    genCode
    0.46
    ﮢ
    0.45
    動物
    0.45
     pomoći
    0.45
    輸出
    0.44
     operazioni
    0.44
    豬
    0.44
    POSITIVE LOGITS
    ↵↵
    0.54
     below
    0.54
     Below
    0.51
    ↵
    0.42
     |
    0.42
     Era
    0.42
     Cy
    0.42
    ↵↵↵
    0.41
     lie
    0.41
     scoreless
    0.41
    Activations Density 0.000%

    No Known Activations