© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12700
    Prev
    Next
    INDEX
    Explanations

    covering something

    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
     бюро
    0.48
    ഽ
    0.43
     tracers
    0.42
     Bureau
    0.41
     혈
    0.40
     BuzzFeed
    0.39
     दाय
    0.39
     알파
    0.39
     opérateurs
    0.38
     нулю
    0.38
    POSITIVE LOGITS
    cover
    0.53
     cover
    0.50
     topped
    0.48
     сверху
    0.48
    蓋
    0.46
    盖
    0.46
     covered
    0.46
     покры
    0.45
    덮
    0.44
    covers
    0.43
    Activations Density 0.057%

    No Known Activations