© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 49474
    Prev
    Next
    INDEX
    Explanations

    Should Be Done

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

    planning, periods, meter, system, charged, company, attitude

    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
    ndor
    0.50
     Peyton
    0.49
     Sheldon
    0.48
    袬
    0.48
     Bezos
    0.47
     Hus
    0.46
     Mein
    0.46
    ementia
    0.45
     مدرس
    0.45
    acom
    0.45
    POSITIVE LOGITS
    뽁
    0.45
    PAK
    0.45
     PROJECTS
    0.45
    ગવાન
    0.45
     phong
    0.44
     opérations
    0.44
    ರುತ್ತವೆ
    0.43
    uettes
    0.43
     TYPES
    0.42
    COMPUTER
    0.42
    Activations Density 0.000%

    No Known Activations