Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12260
    Prev
    Next
    INDEX
    Explanations

    SQL statements

    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_16k_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
     maîtres
    0.45
    linic
    0.43
     unbedingt
    0.42
    မ်
    0.42
    MyToolkit
    0.42
    โครง
    0.41
    㺫
    0.41
     receptionist
    0.41
    AbsolutePath
    0.41
    gena
    0.40
    POSITIVE LOGITS
    目标的
    0.42
     sabiduría
    0.41
     pobres
    0.40
    学习
    0.40
     vítimas
    0.39
    不断
    0.39
    高温
    0.39
     추
    0.38
    DFT
    0.38
    MySQL
    0.38
    Activations Density 0.053%

    No Known Activations