© 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. 106106
    Prev
    Next
    INDEX
    Explanations

    scientific role

    np_acts-logits-general · gemini-2.5-flash-lite

    line/section numbers in code diffs, legal documents, and technical files.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    {\$
    -0.96
    tipped
    -0.79
    נון
    -0.79
    他要
    -0.77
    詫
    -0.76
    他能
    -0.75
     Gamma
    -0.75
    OrDefault
    -0.75
     entra
    -0.75
     Io
    -0.74
    POSITIVE LOGITS
    そして
    0.87
    駛
    0.82
    Studies
    0.81
     plastiques
    0.78
     Autos
    0.77
    踴
    0.76
     recuer
    0.75
     Balla
    0.75
     există
    0.73
    🦷
    0.73
    Activations Density 0.001%

    No Known Activations