© 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. 15664
    Prev
    Next
    INDEX
    Explanations

    technical terms and names

    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
     also
    -1.37
    );
    -1.33
    nadequate
    -1.28
    もあります
    -1.25
     coreano
    -1.24
    Transporte
    -1.22
     decisivo
    -1.20
     hias
    -1.16
     stället
    -1.14
     certainly
    -1.13
    POSITIVE LOGITS
     to
    1.65
     „
    1.42
     \%$
    1.34
     \%$\\
    1.29
    <eos>
    1.29
    ǫ
    1.28
     but
    1.27
    ：……
    1.27
    ně
    1.23
    kön
    1.23
    Activations Density 0.121%

    No Known Activations