© 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. 29915
    Prev
    Next
    INDEX
    Explanations

    dates in November

    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
     Frühjahr
    -0.94
    şağı
    -0.91
     March
    -0.91
     spring
    -0.89
    geſ
    -0.88
     April
    -0.88
     nettsted
    -0.86
    之间
    -0.86
     February
    -0.85
    0
    -0.84
    POSITIVE LOGITS
     Nov
    0.94
    mber
    0.90
    ijų
    0.87
     nove
    0.84
    вят
    0.82
     धन
    0.82
    le
    0.82
     ルーム
    0.80
    ológicos
    0.79
     लिख
    0.79
    Activations Density 0.045%

    No Known Activations