© 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. 5217
    Prev
    Next
    INDEX
    Explanations

    hesitation and questions

    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
     xây
    1.38
     UnwrapRef
    1.35
    tFileInputExcel
    1.34
    នៃការ
    1.33
     khuyến
    1.31
     resaltar
    1.30
     considerando
    1.27
    쨰
    1.27
    녃
    1.26
     hinsichtlich
    1.26
    POSITIVE LOGITS
     they
    1.74
     we
    1.72
     они
    1.65
     it
    1.59
     you
    1.59
     он
    1.54
     is
    1.51
     he
    1.47
     are
    1.46
     она
    1.46
    Activations Density 0.586%

    No Known Activations