© 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. 62674
    Prev
    Next
    INDEX
    Explanations

    flood and disaster reports

    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
    Not in Any Lists

    No Comments

    Negative Logits
     burns
    -0.82
     burning
    -0.81
    jení
    -0.81
     burned
    -0.80
     kebakaran
    -0.77
     Burning
    -0.77
     步
    -0.77
     Selanjutnya
    -0.75
     gels
    -0.74
    projeto
    -0.73
    POSITIVE LOGITS
     maroon
    1.09
     forecast
    0.96
     כן
    0.90
     FORECAST
    0.90
     NDR
    0.87
    Flood
    0.86
     flood
    0.84
     relief
    0.83
     Disaster
    0.82
    かわらず
    0.82
    Activations Density 0.015%

    No Known Activations