© 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. 25233
    Prev
    Next
    INDEX
    Explanations

    min or max values

    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
    Not in Any Lists

    No Comments

    Negative Logits
    niti
    -1.05
     triom
    -1.00
     trom
    -1.00
     industrie
    -0.96
    ӧ
    -0.96
     fiscale
    -0.94
    **
    -0.93
    乁
    -0.93
    妩
    -0.93
    biet
    -0.92
    POSITIVE LOGITS
     still
    0.94
     not
    0.93
     supplement
    0.92
     almost
    0.92
     new
    0.91
     de
    0.90
     advise
    0.88
     roughly
    0.87
     analysis
    0.86
     actually
    0.85
    Activations Density 0.012%

    No Known Activations