© 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. 38698
    Prev
    Next
    INDEX
    Explanations

    at a location

    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
    Not in Any Lists

    No Comments

    Negative Logits
     $
    -2.03
     worauf
    -1.71
     escuchadas
    -1.58
     flexível
    -1.53
     aparência
    -1.53
    wußt
    -1.52
     Publicar
    -1.48
     ofreci
    -1.47
     которая
    -1.47
     desbloquear
    -1.46
    POSITIVE LOGITS
     the
    2.05
     of
    1.88
    是
    1.58
    1
    1.52
     With
    1.48
     each
    1.45
    コスパ
    1.45
     pentru
    1.44
     ricerche
    1.42
     this
    1.34
    Activations Density 0.053%

    No Known Activations