© 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. 224322
    Prev
    Next
    INDEX
    Explanations

    broadphase collision detection

    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
     सूर्
    0.40
     (<
    0.39
     Beh
    0.39
     Governors
    0.39
     Pool
    0.38
     ==>
    0.38
     Philadelphia
    0.37
     Illustration
    0.37
     ಜಿಲ್ಲ
    0.37
     keV
    0.36
    POSITIVE LOGITS
     desigual
    0.43
    椷
    0.43
    优化
    0.42
     своими
    0.41
     Inequal
    0.40
     biodiversity
    0.39
     defrost
    0.39
    杂
    0.39
     dismin
    0.39
     تاسو
    0.39
    Activations Density 0.001%

    No Known Activations