© 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. 48683
    Prev
    Next
    INDEX
    Explanations

    referring to a single item

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

    one

    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
    to
    1.11
    P
    0.98
    s
    0.95
    G
    0.83
    siniz
    0.79
    H
    0.78
    Y
    0.77
    re
    0.77
    F
    0.76
    ra
    0.75
    POSITIVE LOGITS
    데요
    0.76
    надца
    0.69
    jší
    0.67
    ниці
    0.66
    ظ
    0.64
    рики
    0.61
    군요
    0.61
    ிக்க
    0.61
    льники
    0.59
     faciles
    0.59
    Activations Density 0.097%

    No Known Activations