© 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. 32647
    Prev
    Next
    INDEX
    Explanations

    file path components

    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
     from
    -1.20
     in
    -1.13
    傚
    -1.05
    gård
    -1.03
     as
    -1.01
     now
    -1.01
    跌
    -1.00
     it
    -0.94
    yll
    -0.91
     supermercado
    -0.91
    POSITIVE LOGITS
    Instead
    1.09
     かけ
    1.07
     (_)
    1.05
    久しぶりの
    1.02
    Hilsen
    1.02
     evtl
    1.00
    خخ
    0.98
     grima
    0.98
    instead
    0.97
    コロナ禍
    0.95
    Activations Density 0.002%

    No Known Activations