© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68556
    Prev
    Next
    INDEX
    Explanations

    programming code and markup

    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
     if
    -2.09
    máy
    -2.03
    besondere
    -1.99
    
    -1.91
    
    -1.87
    さんで
    -1.86
    sukienka
    -1.85
    䜣
    -1.83
     voordat
    -1.83
    趼
    -1.80
    POSITIVE LOGITS
    </sub>
    2.25
    </strong>
    2.22
    .
    2.17
    </h1>
    2.13
     and
    1.96
    \
    1.95
    ";
    1.95
    }_{
    1.91
     понадоби
    1.82
     внут
    1.77
    Activations Density 0.008%

    No Known Activations