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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 2993
    Prev
    Next
    INDEX
    Explanations

    script tags and bible verses

    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_40_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
    five
    0.12
    கடந்த
    0.12
    al
    0.12
    at
    0.11
    ཌ
    0.11
     ஐந்து
    0.11
     beş
    0.10
    their
    0.10
    ཊ
    0.10
    c
    0.10
    POSITIVE LOGITS
    Você
    0.11
     alphan
    0.10
    /
    0.10
    ления
    0.10
     formatter
    0.10
    You
    0.10
     overcomes
    0.10
    Formatter
    0.10
    Buildings
    0.10
     personnes
    0.09
    Activations Density 0.003%

    No Known Activations