© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150179
    Prev
    Next
    INDEX
    Explanations

    cutting-edge techniques, learning for life, minimize pollution

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

    positive vibes and body language

    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
    抄
    0.46
    ב
    0.46
     File
    0.42
    慶
    0.42
     Progression
    0.41
    export
    0.41
     progress
    0.41
    寫
    0.41
    ʿ
    0.41
     export
    0.40
    POSITIVE LOGITS
    <unused967>
    0.59
    playerName
    0.53
     sizin
    0.50
    cellSize
    0.49
    িমূলক
    0.49
    followlike
    0.49
    selfobj
    0.48
     जुर्माना
    0.48
     gstlal
    0.48
    infoHeader
    0.48
    Activations Density 0.000%

    No Known Activations