© 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. 22499
    Prev
    Next
    INDEX
    Explanations

    integer patterns

    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
    縢
    -2.61
     '"
    -2.52
    荩
    -2.45
    읖
    -2.36
     グリル
    -2.28
    ໊
    -2.14
    
    -2.14
     intric
    -2.13
    dont
    -2.13
     "#
    -2.13
    POSITIVE LOGITS
     your
    2.34
     While
    2.20
    ization
    2.20
    𖥧
    2.13
    梟
    2.13
    蠱
    2.09
    восто
    2.08
    ли
    2.08
    哔
    2.05
     Both
    2.02
    Activations Density 0.006%

    No Known Activations