© 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. 159516
    Prev
    Next
    INDEX
    Explanations

    local businesses, modern wholesalers

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

    characteristics and requirements

    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
     ļ
    0.54
     आरमार
    0.52
     φ
    0.50
     ngắn
    0.50
     ['$
    0.49
     లై
    0.48
    fli
    0.48
     ἡ
    0.48
     ۱
    0.48
    ”،
    0.48
    POSITIVE LOGITS
    کسی
    0.48
    ای
    0.46
     Mountains
    0.45
    土
    0.45
    애
    0.44
    ON
    0.43
    なお
    0.43
    сыпа
    0.42
    Mountains
    0.42
     produce
    0.42
    Activations Density 0.001%

    No Known Activations