© 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-65K
    7. 6054
    Prev
    Next
    INDEX
    Explanations

    https links

    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
    ↵
    0.56
    在
    0.54
    i
    0.53
    是
    0.53
    a
    0.52
    for
    0.51
    l
    0.50
    b
    0.49
    THE
    0.49
    ICS
    0.49
    POSITIVE LOGITS
     on
    0.61
    скую
    0.55
    я
    0.54
    트를
    0.54
     окт
    0.53
    َ
    0.53
     오히려
    0.51
     이날
    0.50
    ме
    0.50
    amı
    0.49
    Activations Density 0.043%

    No Known Activations