© 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. 182713
    Prev
    Next
    INDEX
    Explanations

    activities, Olympics, week, home

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

    organizations and statements

    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
    紳
    0.47
    ształ
    0.46
    freiheit
    0.44
     októ
    0.44
    渟
    0.44
    performance
    0.43
     performans
    0.42
    സിക
    0.42
    분
    0.42
    흔
    0.42
    POSITIVE LOGITS
     религи
    0.48
     FINANCE
    0.44
    滢
    0.44
     quieren
    0.43
    厂家
    0.43
    都会
    0.43
    就要
    0.43
     pandas
    0.41
     sqlite
    0.41
     SQLite
    0.41
    Activations Density 0.001%

    No Known Activations