© 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. 71339
    Prev
    Next
    INDEX
    Explanations

    things falling

    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
    ty
    0.43
    m
    0.41
    tan
    0.40
     typing
    0.40
     sad
    0.39
    tm
    0.39
    arr
    0.39
    t
    0.39
    tel
    0.39
     trigger
    0.38
    POSITIVE LOGITS
    蓯
    0.50
    醤
    0.42
     ترلاسه
    0.40
    睒
    0.40
     deficit
    0.39
    碳
    0.39
    醎
    0.39
    ဈ
    0.38
    怔
    0.38
     entwickelte
    0.37
    Activations Density 0.000%

    No Known Activations