© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108661
    Prev
    Next
    INDEX
    Explanations

    nephro logy

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

    numeric values in technical content like code, documentation, and medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Newt
    -0.81
    二百
    -0.79
    uebas
    -0.73
    凸
    -0.73
    一百
    -0.69
     Hundred
    -0.68
    মান
    -0.68
     hundred
    -0.66
    glä
    -0.66
     Hundreds
    -0.66
    POSITIVE LOGITS
    availability
    0.70
    apha
    0.69
    andro
    0.69
    abolic
    0.67
    PTR
    0.65
     תק
    0.64
    jez
    0.63
    打包
    0.63
    mil
    0.63
    ptr
    0.63
    Activations Density 0.101%

    No Known Activations