© 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. 119354
    Prev
    Next
    INDEX
    Explanations

    Indian states and web URLs

    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
     playmaker
    0.50
     Democrats
    0.44
    ிடம்
    0.44
    电视台
    0.44
    Οι
    0.43
     dizer
    0.43
     dissidents
    0.43
    廛
    0.42
    ைகளைக்
    0.42
     टूर्
    0.41
    POSITIVE LOGITS
     Ramadan
    0.52
     IELTS
    0.49
     Odisha
    0.46
     Eid
    0.46
    Maharashtra
    0.46
     Maharashtra
    0.44
     Gujarat
    0.44
    Rajasthan
    0.43
     Monsoon
    0.43
     Karnataka
    0.42
    Activations Density 0.002%

    No Known Activations