Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 406
    Prev
    Next
    INDEX
    Explanations

    app.use(

    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
    ړه
    0.47
    딨
    0.44
     Fleurit
    0.42
    न्देल
    0.40
    PositionY
    0.40
    สัตว์
    0.40
    蕪
    0.39
    돛
    0.39
    क्षत्र
    0.39
     Chauhan
    0.39
    POSITIVE LOGITS
     '/',
    0.70
    ('/
    0.68
     '/
    0.67
    ('/',
    0.65
     bodyParser
    0.62
     express
    0.61
    bodyParser
    0.61
     "/",
    0.59
    express
    0.57
     cookieParser
    0.55
    Activations Density 0.002%

    No Known Activations