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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8135
    Prev
    Next
    INDEX
    Explanations

    numbers with many zeros

    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_13_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
    on
    2.39
    ition
    2.20
    vio
    2.18
     strang
    2.15
    ings
    2.13
    ope
    2.12
    с
    2.05
    िंक
    2.00
    as
    1.94
    ıcı
    1.94
    POSITIVE LOGITS
    टने
    2.66
    ką
    2.65
    Mâ
    2.63
    entario
    2.54
    нең
    2.53
    kook
    2.48
    ]=[
    2.47
    ค์
    2.45
    ндекс
    2.43
    蚣
    2.43
    Activations Density 0.306%

    No Known Activations