© 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. 6938
    Prev
    Next
    INDEX
    Explanations

    Le, Feliz, Lewin, Specifically, Toler

    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
    {
    -2.38
    calça
    -2.27
     
    -2.25
    沨
    -2.20
     akzeptieren
    -2.14
     pintadas
    -2.08
    独特的
    -2.08
     eds
    -2.05
     createSprite
    -2.02
     kitabı
    -2.02
    POSITIVE LOGITS
    薷
    2.89
    ’
    2.80
     Vergnügen
    2.41
    踯
    2.33
     vostra
    2.33
     occuper
    2.30
    ya
    2.28
    逦
    2.27
    袛
    2.25
     新款
    2.17
    Activations Density 0.000%

    No Known Activations