© 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. 16480
    Prev
    Next
    INDEX
    Explanations

    visual perception

    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
    Radio
    -1.02
     LinkedHashMap
    -0.96
     uomo
    -0.96
     аудио
    -0.95
    inguez
    -0.94
     podcast
    -0.94
    UIButton
    -0.93
     radio
    -0.93
     audiobook
    -0.93
    了些
    -0.92
    POSITIVE LOGITS
     visuals
    1.37
     visual
    1.24
     visually
    1.15
     their
    1.03
    راق
    0.99
    عاون
    0.97
    hetics
    0.97
    metics
    0.93
     videos
    0.92
     zicht
    0.91
    Activations Density 0.093%

    No Known Activations