© 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. 64609
    Prev
    Next
    INDEX
    Explanations

    up to now

    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
    当时
    0.54
    I
    0.53
     temporary
    0.53
    k
    0.50
    old
    0.49
    )).
    0.48
    )"
    0.48
    বর্তমানে
    0.48
     llam
    0.48
     I
    0.48
    POSITIVE LOGITS
     இதுவரை
    0.66
    为止
    0.64
     지금까지
    0.64
     चुके
    0.60
     bisher
    0.60
     تاک
    0.58
     (
    0.55
     hasn
    0.55
     olnud
    0.54
     여기까지
    0.52
    Activations Density 0.012%

    No Known Activations