© 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. 58376
    Prev
    Next
    INDEX
    Explanations

    numbers 336 and 337

    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
    genodigd
    -2.55
    ᐕ
    -2.50
    ᛬
    -2.48
    
    -2.44
    ᨈ
    -2.42
    
    -2.41
    iſter
    -2.41
    鹩
    -2.39
     ſte
    -2.34
    ឵
    -2.30
    POSITIVE LOGITS
    m
    2.36
    ”,
    2.30
    \
    2.27
    T
    2.25
    .”
    2.17
     is
    2.13
    1
    2.02
    Y
    1.96
    ↵↵
    1.95
     =
    1.91
    Activations Density 0.019%

    No Known Activations