© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5956
    Prev
    Next
    INDEX
    Explanations

    predicting expected outcomes

    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
    خرى
    1.84
    jší
    1.70
    h
    1.65
    beri
    1.63
    ں
    1.62
     seca
    1.60
    juk
    1.58
    let
    1.58
    bar
    1.57
    art
    1.56
    POSITIVE LOGITS
    例文帳に追加
    2.64
    ை
    2.58
    ्स
    2.58
     '/'
    2.51
    ाय
    2.50
    ाग्राम
    2.41
    ्त
    2.40
    тан
    2.37
    ास
    2.35
    ิศ
    2.35
    Activations Density 0.174%

    No Known Activations