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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8732
    Prev
    Next
    INDEX
    Explanations

    definitions and properties

    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_31_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
    EnglishMarks
    0.48
     deliverance
    0.47
    userName
    0.46
    getMainUI
    0.45
     sărb
    0.45
     Сьогодні
    0.45
    룔
    0.44
    Сегодня
    0.44
     llevo
    0.43
    stepToken
    0.43
    POSITIVE LOGITS
     anisotropic
    0.46
     $\
    0.46
    与其他
    0.45
     API
    0.44
     None
    0.44
     isomorphisms
    0.44
     isomorphic
    0.44
    \
    0.43
     topological
    0.43
    D
    0.43
    Activations Density 0.002%

    No Known Activations