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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12375
    Prev
    Next
    INDEX
    Explanations

    same number of paths

    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
     TestAvg
    0.40
     ⚫
    0.40
    バランス
    0.40
     Unlike
    0.39
    unlike
    0.38
     unlike
    0.37
    Unlike
    0.36
    Calculate
    0.36
    ٩
    0.36
     عدم
    0.35
    POSITIVE LOGITS
    相同的
    1.63
     same
    1.57
    相同
    1.56
     identical
    1.55
     동일
    1.55
    同じ
    1.48
     hetzelfde
    1.46
     одина
    1.44
    same
    1.43
     samme
    1.39
    Activations Density 1.169%

    No Known Activations