© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    describes actions or functions

    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
    та
    1.73
    られた
    1.73
    то
    1.72
     רא
    1.69
    られました
    1.62
    ta
    1.61
    𝘢
    1.61
    았던
    1.58
    larınız
    1.55
    times
    1.55
    POSITIVE LOGITS
    heet
    2.62
    ometimes
    2.37
    creen
    2.20
    outheast
    2.15
    ettha
    2.10
    ensory
    2.10
    heets
    2.09
    ymbol
    2.02
    íonn
    1.99
    ieht
    1.97
    Activations Density 1.102%

    No Known Activations