© 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. 240892
    Prev
    Next
    INDEX
    Explanations

    sage grouse

    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
     '
    0.52
     research
    0.50
     designate
    0.48
    و
    0.48
     narrative
    0.47
     three
    0.46
    f
    0.46
    ุ
    0.46
    re
    0.45
     other
    0.45
    POSITIVE LOGITS
     స్థాయి
    0.57
     подходя
    0.57
     كرة
    0.56
     adecuadas
    0.55
    వృద్ధి
    0.54
    প্তাহ
    0.53
     během
    0.53
    篮球
    0.53
     నేపథ్యంలో
    0.53
     પૂર્ણ
    0.52
    Activations Density 0.001%

    No Known Activations