© 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. 79546
    Prev
    Next
    INDEX
    Explanations

    XML/JSON namespaces and serialization

    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
    メッセージ
    -0.77
    syms
    -0.75
     Cram
    -0.73
     死
    -0.72
     TSP
    -0.72
    がない
    -0.72
     ナイロン
    -0.71
     выбирать
    -0.71
     ろう
    -0.71
    âge
    -0.70
    POSITIVE LOGITS
     אר
    0.82
    Téléverser
    0.79
    duration
    0.75
     wastewater
    0.73
    aguchi
    0.73
     Ethical
    0.73
    啡
    0.72
    bios
    0.72
     активно
    0.71
     Hebrew
    0.71
    Activations Density 0.074%

    No Known Activations