© 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. 17066
    Prev
    Next
    INDEX
    Explanations

    expert or professional roles

    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
     नया
    0.61
    kontakt
    0.57
     Bupati
    0.57
    ాడు
    0.56
     මු
    0.55
    hj
    0.55
    曈
    0.54
     Der
    0.53
     冬
    0.52
     डोज
    0.52
    POSITIVE LOGITS
     специалистов
    0.87
     chuyên
    0.80
     spécialistes
    0.79
     expertise
    0.77
     specialists
    0.75
     professionals
    0.75
     especialista
    0.75
     experts
    0.74
     전문가
    0.74
     professional
    0.73
    Activations Density 0.146%

    No Known Activations