© 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. 55991
    Prev
    Next
    INDEX
    Explanations

    Lead411 profiles and contact info

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

    app creation tools

    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
    ۳
    0.51
     करत
    0.49
    ⴹ
    0.46
    ብር
    0.44
    ネジ
    0.44
     스
    0.44
    nesota
    0.44
    rocessor
    0.43
    ៨
    0.43
     அவ்வ
    0.43
    POSITIVE LOGITS
     လူ
    0.45
    用戶
    0.45
    texttt
    0.44
     kick
    0.42
    ’
    0.42
     計算
    0.41
     Emir
    0.41
    getTitle
    0.41
    There
    0.41
    替代
    0.41
    Activations Density 0.001%

    No Known Activations