© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12114
    Prev
    Next
    INDEX
    Explanations

    cookie and session management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ান্দ
    0.42
     acetylene
    0.40
     selectInput
    0.39
     команди
    0.39
    indexing
    0.38
     ধাতু
    0.38
     METAL
    0.38
    芑
    0.38
    ‌ర
    0.38
     rhy
    0.38
    POSITIVE LOGITS
     cookies
    2.20
     cookie
    2.19
    Cookie
    2.11
     Cookie
    2.08
     Cookies
    2.06
    Cookies
    1.99
    cookie
    1.95
    cookies
    1.88
    COOKIE
    1.61
    🍪
    1.58
    Activations Density 0.037%

    No Known Activations