© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2114
    Prev
    Next
    INDEX
    Explanations

    d, Mark, Silas, recipes

    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_65k_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
     break
    1.38
     הנו
    1.33
     ն
    1.24
     Theoretically
    1.22
     поэтому
    1.22
    ᅳ
    1.20
     באתר
    1.19
     Nghị
    1.19
     ($_
    1.17
    resto
    1.17
    POSITIVE LOGITS
    elijke
    1.80
    bied
    1.56
    сками
    1.50
     Quadrat
    1.48
    lacht
    1.47
     مخت
    1.47
    ليه
    1.47
     ماس
    1.46
     اربعه
    1.46
    ອາ
    1.45
    Activations Density 0.000%

    No Known Activations