© 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. 127252
    Prev
    Next
    INDEX
    Explanations

    quantifying with ounce

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

    within arteries

    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
    战争
    0.47
    谨慎
    0.46
    잽
    0.43
     chief
    0.41
    珵
    0.41
    紮
    0.40
    勖
    0.40
    VARIABLES
    0.39
    戰爭
    0.39
    撕
    0.39
    POSITIVE LOGITS
    <unused285>
    0.54
     রামগতি
    0.51
     стреми
    0.51
    <unused743>
    0.51
     экрана
    0.50
     مي‌
    0.49
     удаления
    0.49
     ©️
    0.49
     can
    0.48
     صدای
    0.48
    Activations Density 0.001%

    No Known Activations