© 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. 72968
    Prev
    Next
    INDEX
    Explanations

    product descriptions or service features

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

    risk, database, and time

    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
     السياسي
    0.50
    まとめて
    0.46
    😟
    0.46
    ਹੀਂ
    0.46
    ভারতে
    0.45
     gouvernement
    0.44
    ੰਜਾਬ
    0.44
     isra
    0.43
     implications
    0.43
    ِس
    0.42
    POSITIVE LOGITS
    8
    0.55
     maintain
    0.53
     to
    0.52
     Maintain
    0.49
    客户
    0.48
    保持
    0.48
     Width
    0.45
    每天
    0.45
    用户
    0.44
    仅
    0.44
    Activations Density 0.001%

    No Known Activations