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. 12556
    Prev
    Next
    INDEX
    Explanations

    discussion of concepts with indicators

    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
     delf
    0.50
     обеспечение
    0.49
    >`
    0.48
    Roboto
    0.48
    that
    0.47
     distanciation
    0.47
     tigris
    0.47
     jdbcTemplate
    0.46
    訸
    0.46
    ยัง
    0.46
    POSITIVE LOGITS
     pesky
    0.42
    嬠
    0.42
     FAST
    0.40
    urende
    0.40
    ers
    0.40
     පමණ
    0.40
    ersham
    0.40
    rums
    0.39
    Incidentally
    0.39
    ्योर
    0.39
    Activations Density 0.001%

    No Known Activations