© 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. 10-GEMMASCOPE-RES-131K
    7. 38384
    Prev
    Next
    INDEX
    Explanations

    medical conditions

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

    compound words that contain a hyphen (like "tug-of-war" or "per-ihelion").

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    C
    -2.25
     \
    -1.95
    S
    -1.90
     is
    -1.73
    P
    -1.68
     afin
    -1.63
     =>{
    -1.55
     {
    -1.51
     will
    -1.50
     \&
    -1.49
    POSITIVE LOGITS
     that
    1.98
    </sup>
    1.85
     eût
    1.80
     wußte
    1.77
    𓋼
    1.73
     fühlte
    1.71
    极致
    1.70
     voyez
    1.70
    ܃
    1.70
    緜
    1.69
    Activations Density 0.036%

    No Known Activations