© 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. 39453
    Prev
    Next
    INDEX
    Explanations

    rates and utilities

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

    historical names, long-running story, ancient origins, cultural blend, VR walkthroughs

    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
     Chọn
    0.53
    ла
    0.50
     школова
    0.48
     державної
    0.47
     송
    0.46
     Đến
    0.45
     ಪಿ
    0.45
     nghỉ
    0.45
     โจทย์
    0.45
     சுண்ணாம்பு
    0.44
    POSITIVE LOGITS
     unpleasant
    0.47
     pleasant
    0.46
     consumption
    0.44
    мя
    0.44
     pepe
    0.44
    秵
    0.44
    感情
    0.43
    pleasant
    0.43
     comuna
    0.42
     promotions
    0.42
    Activations Density 0.000%

    No Known Activations