© 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. 205949
    Prev
    Next
    INDEX
    Explanations

    items and services

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

    escape the dryer

    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
    Negative Logits
    isa
    0.46
     gotten
    0.45
    ND
    0.45
    OF
    0.44
    /
    0.43
    up
    0.43
    ydi
    0.42
    ;
    0.42
    Ct
    0.42
    yla
    0.42
    POSITIVE LOGITS
    ிறு
    0.58
    низ
    0.52
    olées
    0.50
    ẖ
    0.49
    жность
    0.49
    жности
    0.49
     styleUrls
    0.48
    குதி
    0.48
     Нико
    0.48
    క్షణ
    0.48
    Activations Density 0.001%

    No Known Activations