© 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. 45611
    Prev
    Next
    INDEX
    Explanations

    hexadecimal values and code

    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
     or
    -2.25
     by
    -1.75
     you
    -1.68
     from
    -1.67
     most
    -1.48
     would
    -1.45
     excellent
    -1.39
     analysis
    -1.38
     in
    -1.36
     two
    -1.36
    POSITIVE LOGITS
     crainte
    1.59
     of
    1.53
     allerlei
    1.50
    famille
    1.45
     MAKING
    1.43
     років
    1.43
     acque
    1.41
     blessure
    1.41
     maniere
    1.39
     caráter
    1.39
    Activations Density 0.002%

    No Known Activations