© 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. 34-GEMMASCOPE-RES-131K
    7. 47292
    Prev
    Next
    INDEX
    Explanations

    version tags and identifiers

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     requer
    -0.86
    Taking
    -0.84
     Providing
    -0.84
     exercí
    -0.82
     provide
    -0.82
     suporta
    -0.81
     might
    -0.80
     mengapa
    -0.79
    攫
    -0.78
     beware
    -0.78
    POSITIVE LOGITS
    pub
    0.87
    WinForms
    0.85
     Mora
    0.81
     해
    0.80
     соору
    0.78
     Scopus
    0.77
    rigu
    0.77
    arn
    0.76
     proximal
    0.76
    AYLOR
    0.76
    Activations Density 0.001%

    No Known Activations