© 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. 15019
    Prev
    Next
    INDEX
    Explanations

    varied membership, highest risk, wide range

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

    questions about problems 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
    িকে
    0.47
     interacción
    0.47
    Jazz
    0.46
     জাতিকে
    0.44
    舊
    0.43
     njegove
    0.43
    Maya
    0.42
    솜
    0.42
    ورية
    0.41
     Servi
    0.41
    POSITIVE LOGITS
     ง
    0.47
    ेट्टी
    0.46
    ло
    0.45
    นอก
    0.45
    จอ
    0.44
     Left
    0.44
     run
    0.43
    ۱
    0.43
    rün
    0.42
    बत
    0.42
    Activations Density 0.000%

    No Known Activations