© 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. 854
    Prev
    Next
    INDEX
    Explanations

    bracketed https links

    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
    0.95
     a
    0.93
     to
    0.80
     (
    0.80
     the
    0.78
    :
    0.72
    o
    0.71
    ,
    0.71
     as
    0.69
     [
    0.69
    POSITIVE LOGITS
    ன்ஹீ
    1.61
    𒀊
    1.53
    <unused977>
    1.51
    𒋑
    1.50
    Pksc
    1.50
    𒄬
    1.50
    𒀹
    1.50
    𒅕
    1.50
    𒂆
    1.50
    <unused1516>
    1.49
    Activations Density 0.074%

    No Known Activations