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. 12374
    Prev
    Next
    INDEX
    Explanations

    tool usage and responsibilities

    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
    two
    0.46
    t
    0.41
    five
    0.38
    iin
    0.37
    B
    0.36
    、
    0.36
    Two
    0.36
    b
    0.36
    //
    0.35
    Z
    0.35
    POSITIVE LOGITS
     Persever
    0.40
    thisTrack
    0.39
     اسكت
    0.39
    GoObject
    0.36
     것이다
    0.36
    কিন্ত
    0.35
     Featuring
    0.35
    roduct
    0.34
    酽
    0.34
     Fertilizer
    0.33
    Activations Density 0.052%

    No Known Activations