© 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. 186653
    Prev
    Next
    INDEX
    Explanations

    programming keywords and arguments

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

    function calls or algorithmic terms

    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
     Descripción
    0.43
     Tvam
    0.43
     ampio
    0.43
    让自己
    0.41
     Let
    0.41
     Satu
    0.41
     Atau
    0.40
    庴
    0.40
     Financing
    0.40
     Também
    0.40
    POSITIVE LOGITS
    ({})
    0.42
    ({
    0.39
    EXT
    0.39
    IRS
    0.39
    IBM
    0.38
    BSC
    0.38
    WK
    0.38
    NYSE
    0.37
    BS
    0.37
     beams
    0.37
    Activations Density 0.001%

    No Known Activations