© 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. 1331
    Prev
    Next
    INDEX
    Explanations

    two tired and override

    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
     invoke
    0.58
     koj
    0.57
     elems
    0.54
     ubic
    0.53
     находи
    0.52
    開
    0.51
     compose
    0.50
    逢
    0.50
     form
    0.50
     first
    0.50
    POSITIVE LOGITS
     Appetite
    0.84
     Honestly
    0.80
    Altri
    0.77
    Honestly
    0.75
    voluntary
    0.75
    Numerous
    0.74
     Notably
    0.74
    Useful
    0.73
    <unused463>
    0.73
    <unused723>
    0.73
    Activations Density 0.001%

    No Known Activations