© 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. 79499
    Prev
    Next
    INDEX
    Explanations

    SQL code or technical documentation

    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
    elds
    -0.75
     immunosupp
    -0.74
    Samoa
    -0.72
    prepareStatement
    -0.72
     jednoduch
    -0.71
    落的
    -0.69
    貓
    -0.68
    Alt
    -0.67
    eney
    -0.66
    phoned
    -0.66
    POSITIVE LOGITS
    meisters
    0.85
    érieur
    0.81
    QN
    0.80
    pertoire
    0.73
    rillation
    0.73
    мія
    0.73
     では
    0.73
     NWS
    0.72
     зни
    0.71
     lusso
    0.70
    Activations Density 0.011%

    No Known Activations