© 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. 148813
    Prev
    Next
    INDEX
    Explanations

    multiple things, trash pickup, social anxiety

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

    small or tiny concepts

    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
     austerity
    0.48
     कंट्रोल
    0.46
     tinggal
    0.44
     manipulations
    0.43
    針
    0.43
    非常に
    0.43
    ゲット
    0.43
     altri
    0.42
    🍙
    0.42
     alchemy
    0.42
    POSITIVE LOGITS
    _
    0.55
    ো
    0.49
    dun
    0.49
    RENDER
    0.48
    fta
    0.47
     فِي
    0.47
    so
    0.46
    లుగా
    0.46
    صاب
    0.45
    v
    0.45
    Activations Density 0.001%

    No Known Activations