© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11058
    Prev
    Next
    INDEX
    Explanations

    ISBN or product codes

    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
     竹
    1.60
     花
    1.58
     제도
    1.58
     Bridal
    1.53
     棉
    1.53
     지방
    1.49
     空
    1.49
     布
    1.49
     bridal
    1.46
     한국
    1.46
    POSITIVE LOGITS
     seguramente
    1.11
     pewno
    1.08
     promedio
    1.08
     allgemeinen
    1.04
    म्‍
    1.03
     geral
    1.03
     även
    1.02
    ats
    1.01
    และ
    1.01
    pero
    1.00
    Activations Density 0.000%

    No Known Activations