© 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. 228863
    Prev
    Next
    INDEX
    Explanations

    container, selections, part, malt, suitable, control

    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
    َب
    0.50
    एयर
    0.48
    ᕗ
    0.48
    aziz
    0.48
    手机
    0.47
    objectif
    0.46
    RELATIVA
    0.46
    ጳ
    0.46
     노트북
    0.46
     selepas
    0.45
    POSITIVE LOGITS
     fared
    0.52
     and
    0.50
     inspected
    0.50
     sounded
    0.49
     graced
    0.46
     confers
    0.44
     Bxh
    0.44
     camped
    0.44
     routed
    0.43
    ioned
    0.43
    Activations Density 0.001%

    No Known Activations