© 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. 40-GEMMASCOPE-2-RES-262K
    7. 15700
    Prev
    Next
    INDEX
    Explanations

    お + name, appearance, greetings

    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_40_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
    ⬯
    0.42
     meilleures
    0.42
    轢
    0.42
     anhydride
    0.41
    瑢
    0.41
     quos
    0.41
    陖
    0.40
    分辨率
    0.40
    驪
    0.40
    弹出
    0.40
    POSITIVE LOGITS
    茶
    0.47
    客様
    0.45
    larg
    0.42
    tea
    0.41
    money
    0.40
     tea
    0.40
    offer
    0.39
    상이
    0.38
    каза
    0.38
    follow
    0.38
    Activations Density 0.001%

    No Known Activations