© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11523
    Prev
    Next
    INDEX
    Explanations

    often and donation security

    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_65k_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
    า
    0.54
     Tara
    0.53
    คนที่
    0.49
     частина
    0.49
     Devin
    0.48
     해당하는
    0.48
     Intelig
    0.46
     ک
    0.46
     đựng
    0.46
    芎
    0.46
    POSITIVE LOGITS
    n
    0.48
    reactions
    0.46
    usel
    0.44
    us
    0.44
    ac
    0.43
    hat
    0.43
    org
    0.42
    full
    0.42
    bs
    0.42
    app
    0.41
    Activations Density 0.012%

    No Known Activations