© 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. 10354
    Prev
    Next
    INDEX
    Explanations

    function signatures containing string

    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
    瀉
    0.47
    unità
    0.44
    我不
    0.43
    લ્પ
    0.43
    সিংহ
    0.43
    經歷
    0.42
     جگ
    0.42
     NDVI
    0.42
     ਰ
    0.41
    吹き
    0.41
    POSITIVE LOGITS
    https
    0.48
     घोषणा
    0.47
     champions
    0.46
     referees
    0.45
     https
    0.43
    claimer
    0.43
     Declar
    0.43
    class
    0.42
     declarations
    0.41
     claimants
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.