© 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. 186120
    Prev
    Next
    INDEX
    Explanations

    mobile page

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

    ingredient, cosmetics, peptide, rights, chemical

    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
     پیسہ
    0.55
     ۔
    0.48
     реєстра
    0.47
    ุ่ม
    0.47
     tweeted
    0.46
     설계
    0.45
     ಬಳಕೆ
    0.45
    性感
    0.45
     خس
    0.44
     画像
    0.44
    POSITIVE LOGITS
    wander
    0.52
     Ern
    0.48
    Supp
    0.48
    to
    0.47
    F
    0.47
     Supp
    0.47
    Grand
    0.47
    K
    0.47
    W
    0.46
    Kid
    0.45
    Activations Density 0.003%

    No Known Activations