© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152753
    Prev
    Next
    INDEX
    Explanations

    depressed areas and shadow effects

    np_acts-logits-general · gemini-2.5-flash-lite

    3d border styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resources
    0.50
     bitrate
    0.48
     ie
    0.47
     e
    0.47
     ppm
    0.45
     Bahamas
    0.45
     streaming
    0.44
     analytics
    0.44
     Balkans
    0.44
     ve
    0.44
    POSITIVE LOGITS
    镶
    0.57
    样式
    0.52
     края
    0.50
    इंड
    0.50
    🖌
    0.49
     embossed
    0.49
     внутренней
    0.48
    🖍
    0.48
    interno
    0.48
    面白い
    0.47
    Activations Density 0.001%

    No Known Activations