© 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. 236916
    Prev
    Next
    INDEX
    Explanations

    additional terms

    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
     unsaturated
    0.47
    实现的
    0.46
    вка
    0.46
     artificially
    0.45
    ing
    0.45
     isole
    0.43
     incentiv
    0.43
    ﻗ
    0.43
    利用
    0.43
    bilir
    0.42
    POSITIVE LOGITS
     Tiene
    0.52
     Tämä
    0.52
     Tuple
    0.50
    ายเป็น
    0.49
     keynote
    0.47
     Rahim
    0.47
     วิ
    0.46
     Kilim
    0.46
     Mohammed
    0.46
     semblent
    0.46
    Activations Density 0.000%

    No Known Activations