© 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-16K
    7. 13024
    Prev
    Next
    INDEX
    Explanations

    cache and cookies

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

    data storage and retention

    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_16k_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
    Parsing
    0.52
    豺
    0.46
     подгото
    0.45
    වර
    0.45
    웅
    0.45
    bash
    0.44
    ்ச்ச
    0.43
     இந்ந
    0.43
    幼
    0.43
    枪
    0.43
    POSITIVE LOGITS
     cookie
    1.03
     cookies
    1.02
     Cookie
    1.00
     storage
    0.99
     sessionStorage
    0.98
     storing
    0.96
     almacenamiento
    0.93
     저장
    0.91
     Cookies
    0.89
    存储
    0.88
    Activations Density 0.229%

    No Known Activations