© 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. 91787
    Prev
    Next
    INDEX
    Explanations

    rules, bug, authors

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

    style and precise language

    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
     acclaimed
    0.54
    CAB
    0.54
    CANCEL
    0.53
    เหนือ
    0.52
     selectable
    0.50
    ్ఞ
    0.49
    LJ
    0.49
    Y
    0.49
    NASDAQ
    0.49
    A
    0.49
    POSITIVE LOGITS
    '
    0.64
    ।-
    0.52
    ³.
    0.49
    chnik
    0.46
    '।
    0.46
     രംഗ
    0.44
    ruction
    0.44
     kroppen
    0.43
    ught
    0.43
    ōng
    0.43
    Activations Density 0.000%

    No Known Activations