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. 12397
    Prev
    Next
    INDEX
    Explanations

    birthdays and holidays

    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
    1
    0.56
    Start
    0.50
    Welcome
    0.50
     הן
    0.49
    Run
    0.47
    After
    0.47
     lour
    0.47
    The
    0.46
     לאחר
    0.45
    ↵
    0.45
    POSITIVE LOGITS
     creates
    0.49
     approche
    0.48
     ({\
    0.48
    robes
    0.48
    слен
    0.47
     effect
    0.47
    кла
    0.46
     claws
    0.46
    ೊಳ
    0.46
     interferes
    0.46
    Activations Density 0.114%

    No Known Activations