© 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. 26761
    Prev
    Next
    INDEX
    Explanations

    opening parentheses

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

    parentheses enclosing options

    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
     неф
    0.52
    ❒
    0.52
    سے
    0.52
    鰱
    0.52
    ком
    0.51
    تها
    0.51
    🩺
    0.51
    нов
    0.50
    ،
    0.50
    鉭
    0.48
    POSITIVE LOGITS
     혹은
    0.61
    もしくは
    0.50
     ಬರುತ್ತ
    0.48
     또는
    0.47
    又は
    0.47
    （
    0.47
     이는
    0.45
     N
    0.45
     포함
    0.45
    ※
    0.45
    Activations Density 0.012%

    No Known Activations