© 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. 222140
    Prev
    Next
    INDEX
    Explanations

    describes standards and requirements

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

    Russian oil

    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
     alá
    0.54
     generan
    0.52
     inade
    0.52
     messes
    0.50
    िटी
    0.50
    isinin
    0.49
     součástí
    0.49
    ử
    0.49
     uter
    0.48
     AFD
    0.48
    POSITIVE LOGITS
     Lib
    0.42
    tempHeader
    0.42
    予定
    0.41
    berra
    0.40
    reverse
    0.39
     Campo
    0.39
     La
    0.38
    ram
    0.38
    tsch
    0.38
    sole
    0.38
    Activations Density 0.001%

    No Known Activations