© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8637
    Prev
    Next
    INDEX
    Explanations

    cookies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     INumber
    0.63
    Tensor
    0.63
     верши
    0.62
     xgboost
    0.62
     XLR
    0.60
    鷹
    0.60
     Presidents
    0.59
    PatientR
    0.59
    愤
    0.59
     הפ
    0.58
    POSITIVE LOGITS
     cookies
    2.50
     cookie
    2.45
     Cookies
    2.16
    cookies
    2.16
    cookie
    2.14
    Cookie
    2.13
     Cookie
    2.11
    Cookies
    2.06
    🍪
    1.77
    COOKIE
    1.48
    Activations Density 0.128%

    No Known Activations