© 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. 7720
    Prev
    Next
    INDEX
    Explanations

    display related terms

    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
    ಬ್ಬಿಣ
    0.45
    Course
    0.42
    ೂರಿನ
    0.39
     Course
    0.38
     কোর্স
    0.38
    ᚑ
    0.38
    骖
    0.37
    तमंद
    0.37
    course
    0.37
    bsch
    0.37
    POSITIVE LOGITS
     displays
    0.42
    ↵
    0.40
     Kate
    0.37
     Display
    0.36
     disallowed
    0.36
    ↵↵
    0.36
    ↵↵↵
    0.36
     display
    0.35
     Math
    0.35
     Kue
    0.35
    Activations Density 0.003%

    No Known Activations