© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25908
    Prev
    Next
    INDEX
    Explanations

    items following punctuation

    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_22/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
    
    -1.77
    Semua
    -1.75
    Ꮠ
    -1.66
    Jawab
    -1.62
    鰱
    -1.61
    Jangan
    -1.59
    我們
    -1.59
    Gör
    -1.59
    鷭
    -1.59
    accesorios
    -1.58
    POSITIVE LOGITS
    '
    1.88
    H
    1.67
     It
    1.56
    ​
    1.55
    ...
    1.55
      
    1.54
    --
    1.45
    T
    1.42
    G
    1.41
     V
    1.40
    Activations Density 0.007%

    No Known Activations