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. 12398
    Prev
    Next
    INDEX
    Explanations

    tables summarizing differences

    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
    窰
    0.42
     \%
    0.39
     थ्री
    0.39
     Crohn
    0.38
     MSRP
    0.38
     Treating
    0.37
    第一次
    0.37
     घाटी
    0.36
     лечения
    0.36
    বৈশাখ
    0.36
    POSITIVE LOGITS
     để
    0.50
    ك
    0.49
     đầy
    0.44
     conquistar
    0.43
    ק
    0.43
    по
    0.43
     este
    0.42
    ي
    0.42
     posible
    0.41
    serialized
    0.41
    Activations Density 0.009%

    No Known Activations