© 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. 78612
    Prev
    Next
    INDEX
    Explanations

    awaiting things

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

    casual & familiar language

    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
     पहनने
    0.50
    ก็
    0.48
    où
    0.46
    deviceId
    0.46
    sunline
    0.44
    selectable
    0.44
    嶷
    0.44
    лана
    0.43
    തമായ
    0.43
    ㅝ
    0.43
    POSITIVE LOGITS
     withdrawals
    0.52
     birthdays
    0.47
    的他
    0.45
     allotments
    0.45
     pilgr
    0.44
     acoustics
    0.44
     entrop
    0.44
     pastries
    0.43
     واله
    0.43
     refunds
    0.42
    Activations Density 0.001%

    No Known Activations