© 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. 53-GEMMASCOPE-2-RES-262K
    7. 10091
    Prev
    Next
    INDEX
    Explanations

    falling, stumbling, tripping, tumbling

    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_53_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
    IsNullOr
    0.42
    setBadgeText
    0.40
     Stateful
    0.39
     రూ
    0.38
     විය
    0.38
    韜
    0.37
    :@"
    0.37
     injective
    0.36
    誨
    0.36
    刊
    0.36
    POSITIVE LOGITS
     tumbling
    1.72
     tumbled
    1.70
     tumble
    1.68
    摔
    1.59
     stumble
    1.55
    跌
    1.52
     falling
    1.52
     falls
    1.51
     سقوط
    1.45
     fall
    1.41
    Activations Density 0.059%

    No Known Activations