© 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. 15658
    Prev
    Next
    INDEX
    Explanations

    git branch

    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
    Negative Logits
    が進
    -2.80
    pentru
    -2.78
    鲧
    -2.42
     každý
    -2.42
    癭
    -2.38
    
    -2.36
     jiné
    -2.34
    銦
    -2.34
    amoan
    -2.31
    糌
    -2.31
    POSITIVE LOGITS
    h
    4.28
    \
    3.73
    ).
    3.48
    ;
    3.42
    s
    3.34
    w
    3.22
    y
    3.08
    。
    3.03
    An
    3.00
    man
    2.88
    Activations Density 0.007%

    No Known Activations