© 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. 1923
    Prev
    Next
    INDEX
    Explanations

    information and conversion

    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
    BackgroundHelper
    0.56
     设备
    0.54
     ausschließlich
    0.52
     lưu
    0.48
     hva
    0.47
     устройства
    0.47
    ">-
    0.46
     allevi
    0.46
     电
    0.46
    丢失
    0.46
    POSITIVE LOGITS
    st
    0.60
    TL
    0.55
    end
    0.55
    k
    0.55
    uk
    0.55
    tes
    0.54
    om
    0.54
    EB
    0.54
    ately
    0.53
    ys
    0.52
    Activations Density 0.000%

    No Known Activations