© 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. 106304
    Prev
    Next
    INDEX
    Explanations

    rights and license information

    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
     turbine
    -0.73
    Hall
    -0.72
     Turbine
    -0.69
     HALL
    -0.68
     Haller
    -0.66
    Ingredi
    -0.66
    standard
    -0.66
     Burs
    -0.66
     захворювання
    -0.65
    ائے
    -0.65
    POSITIVE LOGITS
     bed
    1.03
     Bed
    0.80
    𝖓
    0.71
    Bed
    0.69
    bed
    0.69
    队友
    0.67
    ilai
    0.66
    bound
    0.66
    Descriptor
    0.65
    FTW
    0.65
    Activations Density 0.042%

    No Known Activations