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. 12545
    Prev
    Next
    INDEX
    Explanations

    price changes and quotes

    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
    i
    0.64
    ید
    0.61
    ي
    0.61
    sad
    0.60
    هره
    0.58
     estancia
    0.57
    goed
    0.56
    eso
    0.55
    slee
    0.55
    the
    0.55
    POSITIVE LOGITS
    of
    0.75
    ни
    0.64
    一种
    0.59
    变化
    0.56
     Biochem
    0.54
     रामानंद
    0.54
    ли
    0.53
    莴
    0.53
    il
    0.52
    变化的
    0.52
    Activations Density 0.228%

    No Known Activations