© 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. 191459
    Prev
    Next
    INDEX
    Explanations

    integral over a closed surface

    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
     mMap
    0.46
    bookmarks
    0.43
    markUp
    0.42
    }}=-
    0.41
    പക്ഷം
    0.41
    শ্ব
    0.40
    ừng
    0.40
    шка
    0.39
    шки
    0.39
    日前
    0.38
    POSITIVE LOGITS
    фей
    0.40
    Gil
    0.40
     επο
    0.37
     перспекти
    0.35
    复制
    0.35
    فة
    0.35
     Essentially
    0.35
     noção
    0.35
    离
    0.35
    離
    0.34
    Activations Density 0.001%

    No Known Activations