© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15322
    Prev
    Next
    INDEX
    Explanations

    Arabic names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     THR
    0.69
      
    0.66
     int
    0.65
     s
    0.62
     $
    0.62
     partic
    0.61
     major
    0.61
     vent
    0.61
    -
    0.61
     point
    0.60
    POSITIVE LOGITS
    awi
    0.83
    ناوی
    0.82
    ouni
    0.77
     அல்
    0.74
    ساوي
    0.73
    Allah
    0.73
    itani
    0.73
    awy
    0.73
     مخلو
    0.72
    adeh
    0.71
    Activations Density 0.058%

    No Known Activations