© 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. 56799
    Prev
    Next
    INDEX
    Explanations

    in question or described

    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
     tijdens
    -0.93
     cremallera
    -0.82
    mlı
    -0.82
     réfrig
    -0.82
     Answered
    -0.79
     بعد
    -0.79
    dentro
    -0.79
    Inp
    -0.78
    ihnachten
    -0.77
    вшись
    -0.76
    POSITIVE LOGITS
     in
    2.95
     concerned
    2.59
    concerned
    1.94
     involved
    1.65
     dimaksud
    1.64
     questioned
    1.63
     question
    1.56
     offending
    1.45
     mentioned
    1.45
     referred
    1.40
    Activations Density 0.080%

    No Known Activations