© 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. 4353
    Prev
    Next
    INDEX
    Explanations

    hotlines and support numbers

    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
    㓶
    0.31
    🥢
    0.31
    栊
    0.30
    जूदा
    0.30
    㬹
    0.29
    峼
    0.29
     ویئر
    0.29
    ेंटीना
    0.29
    🦑
    0.28
    VerFile
    0.28
    POSITIVE LOGITS
    s
    0.39
    sc
    0.34
    sa
    0.33
    of
    0.32
    p
    0.32
    t
    0.32
    and
    0.31
    other
    0.31
    sk
    0.30
    d
    0.30
    Activations Density 0.060%

    No Known Activations