© 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-262K
    7. 200520
    Prev
    Next
    INDEX
    Explanations

    legend, title, header

    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_262k_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
     풀
    0.51
     가장
    0.45
     каждом
    0.43
     pagos
    0.43
     칸
    0.43
    𝗁
    0.43
     영상
    0.42
     внешний
    0.42
    leye
    0.42
     ها
    0.41
    POSITIVE LOGITS
     Idee
    0.51
     }^{
    0.46
    指针
    0.46
     Radio
    0.46
     Burton
    0.44
     aromat
    0.44
     sotto
    0.44
     Sevent
    0.44
     Phil
    0.43
     Soviet
    0.43
    Activations Density 0.003%

    No Known Activations