© 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. 41172
    Prev
    Next
    INDEX
    Explanations

    setting a precedent

    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
    o
    1.63
    a
    1.55
     is
    1.38
    at
    1.29
    s
    1.29
    e
    1.11
    an
    1.08
     to
    1.06
     has
    1.06
    to
    1.06
    POSITIVE LOGITS
    的光
    1.07
    Những
    1.05
    的结果
    1.03
    푞
    1.03
    Ин
    0.98
    Công
    0.94
    Με
    0.93
    ജീവ
    0.91
    ”،
    0.89
    သွယ်
    0.89
    Activations Density 0.001%

    No Known Activations