© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17449
    Prev
    Next
    INDEX
    Explanations

    manicured appearance

    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_16_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
    션을
    0.83
    션
    0.73
    Bine
    0.73
    众
    0.73
    шель
    0.72
    ভৌম
    0.71
     médio
    0.70
     لیګ
    0.69
     сеть
    0.69
    ARD
    0.68
    POSITIVE LOGITS
    د
    1.07
    ل
    0.88
     in
    0.86
    io
    0.84
    ん
    0.84
    ul
    0.81
    ä
    0.80
    un
    0.77
    :
    0.75
    س
    0.74
    Activations Density 0.000%

    No Known Activations