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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7463
    Prev
    Next
    INDEX
    Explanations

    book book

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    𝙡
    1.41
    night
    1.34
     обстанов
    1.28
    מ
    1.26
    NESS
    1.25
    이나
    1.25
     vínculos
    1.24
    nent
    1.19
    Си
    1.19
    agir
    1.18
    POSITIVE LOGITS
    e
    1.27
    eo
    1.22
    ள்ளது
    1.12
    eenth
    1.12
     풍
    1.11
     charcoal
    1.09
    க்கொண்ட
    1.09
    ছিলেন
    1.08
    u
    1.06
     staple
    1.06
    Activations Density 0.000%

    No Known Activations