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. 84900
    Prev
    Next
    INDEX
    Explanations

    mission objectives

    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
    Connect
    0.55
    ഗം
    0.47
    '
    0.45
    O
    0.43
    タック
    0.42
    Combine
    0.42
    Conte
    0.42
    iles
    0.41
    ’
    0.41
    Grad
    0.41
    POSITIVE LOGITS
    잎
    0.60
    də
    0.54
     unmarried
    0.52
    χρο
    0.48
    cích
    0.48
    苍
    0.48
    蚜
    0.47
    scorpion
    0.47
    年份
    0.47
    dé
    0.46
    Activations Density 0.001%

    No Known Activations