© 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. 45570
    Prev
    Next
    INDEX
    Explanations

    function 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
    Begriffsklä
    -1.59
     famosas
    -1.52
     fís
    -1.48
     various
    -1.48
    şam
    -1.47
     camión
    -1.46
     которы
    -1.39
    homonymie
    -1.38
     préstamos
    -1.36
     biggest
    -1.35
    POSITIVE LOGITS
    ’
    1.65
    '
    1.61
    in
    1.59
    7
    1.58
    ner
    1.44
    :
    1.36
    ,”
    1.33
    $
    1.33
    put
    1.32
    All
    1.32
    Activations Density 0.002%

    No Known Activations