© 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. 155904
    Prev
    Next
    INDEX
    Explanations

    management, potential, Infinity Ward, birthday

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

    steadfast partner

    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
    تي
    0.53
    تج
    0.52
    ت
    0.52
    տ
    0.50
    طة
    0.50
    ط
    0.50
    ת
    0.50
    بة
    0.48
    제품
    0.47
    九
    0.47
    POSITIVE LOGITS
    -
    0.48
    VO
    0.48
     quand
    0.44
    ild
    0.43
    issons
    0.43
    พอ
    0.43
    CONDS
    0.42
    allist
    0.42
     завер
    0.42
    elab
    0.42
    Activations Density 0.001%

    No Known Activations