© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13061
    Prev
    Next
    INDEX
    Explanations

    a)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    لم
    2.82
    ית
    2.66
    ി
    2.62
    みに
    2.59
    푎
    2.58
    Fet
    2.54
    يدا
    2.50
    يد
    2.48
    ו
    2.48
    া
    2.45
    POSITIVE LOGITS
    ছিলো
    2.87
    ब्दिक
    2.76
    łoś
    2.68
    łącz
    2.58
    ścia
    2.58
    шай
    2.57
    zieć
    2.56
    tochy
    2.55
    ging
    2.54
    /{
    2.51
    Activations Density 0.014%

    No Known Activations