© 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. 152771
    Prev
    Next
    INDEX
    Explanations

    manual online

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

    pockets of the, directory of, hidden

    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
    Waters
    0.52
    Plants
    0.52
    Gr
    0.49
    Cursor
    0.49
     Plants
    0.49
    Bp
    0.48
     {
    0.46
    Sav
    0.46
    ít
    0.46
    N
    0.45
    POSITIVE LOGITS
     hemicontinuous
    0.52
     retrait
    0.52
     determinante
    0.51
     cárc
    0.50
    른
    0.48
     उल
    0.46
     gerçekten
    0.46
    ना
    0.46
     மிசோ
    0.46
     були
    0.45
    Activations Density 0.000%

    No Known Activations