© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93041
    Prev
    Next
    INDEX
    Explanations

    error rates and significance

    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
     estime
    -0.97
     pontu
    -0.81
     suav
    -0.77
    trust
    -0.75
     femen
    -0.75
     instin
    -0.73
    ό
    -0.72
     WARRANT
    -0.72
    nig
    -0.70
    cketed
    -0.70
    POSITIVE LOGITS
     Type
    1.67
    Type
    1.31
     Errors
    1.15
     reject
    1.13
     error
    1.11
     rejection
    1.09
     Rejection
    1.07
     alpha
    1.05
     rejecting
    1.04
    错误
    1.02
    Activations Density 0.017%

    No Known Activations