© 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. 31928
    Prev
    Next
    INDEX
    Explanations

    Mark and Zhang

    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
    at
    1.44
    ل
    1.32
    pengaruhi
    1.09
    ৭
    1.09
     밝혔
    1.04
    ט
    1.04
    ३
    0.95
    ла
    0.91
    ર
    0.89
    ९
    0.89
    POSITIVE LOGITS
    '
    1.47
     I
    1.26
    s
    1.11
    1
    1.02
    o
    1.01
    I
    1.00
    不
    0.95
    する
    0.94
    able
    0.93
     Tử
    0.92
    Activations Density 0.001%

    No Known Activations