© 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. 40604
    Prev
    Next
    INDEX
    Explanations

    achievements and ongoing actions

    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
     เช่น
    0.49
     यानी
    0.48
    :
    0.46
     약
    0.43
     లేదా
    0.42
     italics
    0.42
     çünkü
    0.42
    because
    0.42
    ：
    0.42
     زیرا
    0.42
    POSITIVE LOGITS
     Nachdem
    0.46
     began
    0.43
     chose
    0.42
     выбира
    0.41
     केल्यानंतर
    0.40
    Roxy
    0.40
    спользу
    0.40
     everytime
    0.39
    ụng
    0.39
     использует
    0.38
    Activations Density 0.029%

    No Known Activations