© 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. 49246
    Prev
    Next
    INDEX
    Explanations

    TVs and streaming services

    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
     விவசாய
    0.51
     डेस्क
    0.46
     midwifery
    0.46
     Workplace
    0.46
     Workspace
    0.45
     cellulaire
    0.45
    页
    0.45
     खेतों
    0.42
    뉜
    0.42
     кеңсе
    0.42
    POSITIVE LOGITS
     TV
    0.73
    TV
    0.68
     TVs
    0.68
     IPTV
    0.62
     HDTV
    0.61
     tv
    0.61
    HDMI
    0.56
     Roku
    0.54
    tv
    0.54
     Netflix
    0.54
    Activations Density 0.095%

    No Known Activations