© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58290
    Prev
    Next
    INDEX
    Explanations

    code block start syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    酩
    -2.88
    残酷
    -2.53
    Y
    -2.42
    逡
    -2.28
    忖
    -2.27
    R
    -2.17
    V
    -2.16
     Because
    -2.13
     How
    -2.11
    なので
    -2.08
    POSITIVE LOGITS
    ти
    2.70
    ль
    2.58
    ’
    2.41
    ᠂
    2.33
     или
    2.28
     "...
    2.22
     huéspedes
    2.19
     fatos
    2.19
     machten
    2.17
    雱
    2.17
    Activations Density 0.008%

    No Known Activations