© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    class followed by entity names

    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
    想到
    1.64
    щий
    1.59
    ుడు
    1.56
    <()>
    1.53
    щее
    1.53
    iros
    1.48
    绀
    1.46
    шель
    1.46
    吠
    1.44
    chts
    1.44
    POSITIVE LOGITS
    eless
    1.66
    ging
    1.60
    ەی
    1.53
    ཆ
    1.50
    unt
    1.48
     כן
    1.44
    abook
    1.42
    ernacle
    1.42
    deviceName
    1.41
    dynam
    1.38
    Activations Density 0.011%

    No Known Activations