© 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. 79984
    Prev
    Next
    INDEX
    Explanations

    crowd/broad/budget/enlightenment context

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

    changes and descriptions

    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
     inquiet
    0.52
     estime
    0.51
     एन्
    0.49
    encript
    0.49
     consid
    0.48
    {#
    0.48
    saraba
    0.48
     изпол
    0.46
    congress
    0.46
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.46
    POSITIVE LOGITS
    粦
    0.55
    сть
    0.45
     Wall
    0.45
     WALL
    0.43
     impressively
    0.43
    ிகளுக்கு
    0.42
    此同时
    0.42
     Doubt
    0.41
     Easier
    0.40
     Percentage
    0.40
    Activations Density 0.000%

    No Known Activations