© 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. 8306
    Prev
    Next
    INDEX
    Explanations

    champion of patient

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

    combinatorial features, laws enacted, power, details

    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
    rench
    0.44
    สดง
    0.42
    GIS
    0.41
     Gis
    0.40
    条件
    0.39
     gis
    0.39
    越
    0.39
    ﺝ
    0.39
     uomo
    0.38
    ltk
    0.38
    POSITIVE LOGITS
     vriend
    0.43
     Friend
    0.42
     Circles
    0.41
     cír
    0.40
     друзей
    0.40
     tervez
    0.39
     PUL
    0.39
     FRIEND
    0.39
     friend
    0.38
     circol
    0.38
    Activations Density 0.000%

    No Known Activations