© 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. 11158
    Prev
    Next
    INDEX
    Explanations

    social media platform links

    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
    ită
    0.48
     яс
    0.47
    ರುವುದು
    0.45
     дві
    0.45
    ympt
    0.45
    ťa
    0.44
    젝
    0.44
    хема
    0.43
    ನದ
    0.43
    Además
    0.43
    POSITIVE LOGITS
    -
    0.52
    由
    0.50
    采用
    0.46
     由
    0.45
    配备
    0.41
    公司
    0.40
     adopts
    0.40
     কোম্প
    0.40
    通讯
    0.39
     organizacional
    0.39
    Activations Density 0.009%

    No Known Activations