© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    tasks with enthusiasm

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
     Ở
    0.70
    Ở
    0.68
     Öğ
    0.61
     ở
    0.60
    อ่อน
    0.59
    JSONObject
    0.58
     Ông
    0.58
     ovvero
    0.56
    欧
    0.55
     oito
    0.55
    POSITIVE LOGITS
    -------
    0.48
    Б
    0.46
    কিন্তু
    0.44
    latitude
    0.43
     наблюда
    0.43
               
    0.42
     -------
    0.41
     પણ
    0.41
    ränkt
    0.41
    randn
    0.40
    Activations Density 0.281%

    No Known Activations