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. 22-GEMMASCOPE-2-RES-16K
    4. 125
    Prev
    Next
    INDEX
    Explanations

    various languages, technical terms

    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_22_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
     (
    0.98
     either
    0.97
     s
    0.90
     slightly
    0.90
     around
    0.90
     e
    0.89
     i
    0.89
     on
    0.88
     in
    0.83
     [
    0.82
    POSITIVE LOGITS
    <end_of_turn>
    1.11
    zení
    1.10
    氀
    1.04
    šnji
    1.03
    łek
    1.03
    altezza
    1.02
    okkal
    1.02
    BufferedReader
    1.02
    Typography
    1.02
    agę
    1.02
    Activations Density 0.536%

    No Known Activations