© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3740
    Prev
    Next
    INDEX
    Explanations

    crucial or crucially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    รส
    0.62
    usine
    0.60
     priorities
    0.58
    hrung
    0.57
     tastes
    0.56
    ?;
    0.56
    र्की
    0.56
     thermostats
    0.55
     abar
    0.53
     আপ
    0.53
    POSITIVE LOGITS
    ually
    0.77
     Officially
    0.73
    ്‍
    0.69
     GLFW
    0.69
    iffe
    0.69
     प्रीम
    0.68
     linebreak
    0.68
    Book
    0.68
     oficiais
    0.67
    geb
    0.67
    Activations Density 0.075%

    No Known Activations