© 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. 22-GEMMASCOPE-RES-131K
    7. 24946
    Prev
    Next
    INDEX
    Explanations

    route, JSON, capabilities, load, select

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     hemd
    -1.65
     eenen
    -1.64
     hunne
    -1.63
    蛱
    -1.59
    蟥
    -1.59
    鸸
    -1.52
     vorige
    -1.50
     siè
    -1.50
     frança
    -1.46
     restant
    -1.44
    POSITIVE LOGITS
    Some
    1.98
    One
    1.91
    Every
    1.77
    Many
    1.75
    Several
    1.73
    Although
    1.69
    Nearly
    1.68
    Very
    1.66
     what
    1.65
    Almost
    1.65
    Activations Density 0.001%

    No Known Activations