© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25976
    Prev
    Next
    INDEX
    Explanations

    medical, biological, or contractual functions

    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_262k_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
     החד
    0.50
     biomark
    0.46
     обычно
    0.44
     kawaida
    0.41
     публикации
    0.40
     лицо
    0.39
     чаще
    0.39
    釈
    0.39
    icu
    0.39
     ብዙውን
    0.39
    POSITIVE LOGITS
     flooring
    0.47
     protects
    0.46
     equipes
    0.44
     will
    0.41
     amén
    0.41
     ensures
    0.40
     is
    0.40
     বিদ্যালয়ে
    0.40
    予以
    0.39
     ensure
    0.39
    Activations Density 0.009%

    No Known Activations