© 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. 2449
    Prev
    Next
    INDEX
    Explanations

    contractions with let

    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
    astava
    1.21
    氅
    1.11
    mui
    1.07
     पूर्वी
    1.05
    ukkh
    1.04
    pectral
    1.03
    ()['
    1.00
    ylsulfanyl
    0.99
    तून
    0.96
    <table>
    0.96
    POSITIVE LOGITS
     your
    2.12
     yourself
    2.02
     YOUR
    1.88
     votre
    1.85
     Yourself
    1.85
    your
    1.81
     пожалуйста
    1.80
    yourself
    1.77
     yourselves
    1.77
     vos
    1.75
    Activations Density 1.721%

    No Known Activations