© 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. 5350
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions

    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
    aysia
    0.42
    jaya
    0.41
    澱
    0.41
    atthena
    0.40
     {}>,
    0.40
    ంతరం
    0.40
    soil
    0.40
    ursery
    0.39
    dust
    0.39
    POSITIVE LOGITS
    /**
    0.46
     Schreiben
    0.45
     vurg
    0.45
     ise
    0.44
    Н
    0.43
     emphasize
    0.43
     Тео
    0.43
     emph
    0.42
     У
    0.42
     emphasized
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.