© 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. 106291
    Prev
    Next
    INDEX
    Explanations

    joins people and partners

    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
     by
    -0.94
     on
    -0.84
     from
    -0.81
     sogenannten
    -0.79
     Gå
    -0.78
     https
    -0.77
    ūt
    -0.77
     промо
    -0.77
     sogenannte
    -0.76
     From
    -0.73
    POSITIVE LOGITS
     Dave
    1.13
     allons
    1.11
    itaji
    1.03
     cukru
    1.02
    Todd
    1.02
     Jeff
    0.98
     sóc
    0.97
     Chad
    0.97
     jeste
    0.96
     jaka
    0.95
    Activations Density 0.061%

    No Known Activations