© 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-16K
    7. 8821
    Prev
    Next
    INDEX
    Explanations

    Korean author author

    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
     productive
    1.35
     primaryStage
    1.33
    aduct
    1.31
     revived
    1.30
    м
    1.30
     unproductive
    1.30
    ત્રો
    1.29
    涅
    1.28
     nonspecific
    1.27
    רק
    1.25
    POSITIVE LOGITS
    idad
    1.59
    ্কার
    1.39
    sticker
    1.39
     appartiennent
    1.39
     달
    1.36
    COLL
    1.35
    ccedil
    1.35
     igu
    1.33
     säker
    1.30
    GT
    1.30
    Activations Density 0.000%

    No Known Activations