© 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. 19569
    Prev
    Next
    INDEX
    Explanations

    definitions and technical terms

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

    function to, documented REST, trained on, regular expression

    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
    :
    0.44
     वॉटर
    0.35
     queryString
    0.34
     runnable
    0.33
     tzv
    0.33
     ဒါ
    0.33
    :.
    0.33
     micrographs
    0.32
     Electrode
    0.32
    :”
    0.32
    POSITIVE LOGITS
    iswa
    0.41
    pe
    0.40
    스
    0.36
     специальности
    0.35
    は大
    0.33
    澳
    0.33
    ب
    0.32
    Zum
    0.31
    Deze
    0.31
    훼
    0.31
    Activations Density 0.027%

    No Known Activations