© 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. 106260
    Prev
    Next
    INDEX
    Explanations

    legal, licensing, or structured text elements

    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
    不堪
    -0.73
    responseBody
    -0.71
    ੌ
    -0.69
    THEORY
    -0.68
     sudad
    -0.68
    Dise
    -0.67
    contoh
    -0.66
    gathered
    -0.65
    coaster
    -0.65
    Fit
    -0.64
    POSITIVE LOGITS
     Faro
    0.72
     Anastasia
    0.66
    coll
    0.65
     Mateo
    0.65
    엌
    0.64
     dict
    0.64
     diferen
    0.64
     borealis
    0.63
     worried
    0.62
    Dup
    0.62
    Activations Density 0.103%

    No Known Activations