© 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. 71377
    Prev
    Next
    INDEX
    Explanations

    device or system function

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

    character development

    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
     몸
    0.58
    身體
    0.57
     미국
    0.50
    Otra
    0.49
     अमेर
    0.49
     मस्तिष्क
    0.48
    ব্রিটিশ
    0.48
    明顯
    0.48
    ジュ
    0.47
     자연
    0.47
    POSITIVE LOGITS
    c
    0.54
    e
    0.50
    t
    0.49
    io
    0.48
    an
    0.45
     swath
    0.45
     stif
    0.44
    aul
    0.44
    ́s
    0.43
    ek
    0.43
    Activations Density 0.001%

    No Known Activations