© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13552
    Prev
    Next
    INDEX
    Explanations

    Did followed by country

    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
     UTIL
    0.42
     Valentina
    0.42
     Udaipur
    0.41
     Ultrasound
    0.40
     ulcers
    0.40
     Util
    0.40
    Ｕ
    0.40
     traceability
    0.40
     Timurtaş
    0.39
    linkCell
    0.39
    POSITIVE LOGITS
    widget
    0.62
    Widget
    0.49
     Widget
    0.46
     widget
    0.46
     ward
    0.42
     w
    0.40
     Wester
    0.39
     wonderful
    0.39
     welcoming
    0.39
     wage
    0.38
    Activations Density 0.001%

    No Known Activations