© 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. 1086
    Prev
    Next
    INDEX
    Explanations

    xml namespace prefixes

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

    <!DOCTYPE html>

    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
     تړ
    0.46
    篪
    0.46
     Tattha
    0.46
     تړل
    0.45
    鉭
    0.45
    वीण
    0.45
    거리
    0.44
     Теннис
    0.44
    وفيق
    0.43
    Якщо
    0.43
    POSITIVE LOGITS
     xml
    0.52
    xml
    0.52
     w
    0.49
     M
    0.46
    x
    0.46
     th
    0.45
    DOCTYPE
    0.44
     x
    0.43
     H
    0.42
     N
    0.41
    Activations Density 0.000%

    No Known Activations