© 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. 8101
    Prev
    Next
    INDEX
    Explanations

    fastapi import

    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
     expenditure
    1.70
    ీ
    1.70
    되었다
    1.61
    otransferase
    1.61
    될
    1.58
    되지
    1.56
     terminals
    1.55
     Expenditure
    1.55
    iblock
    1.55
    된
    1.54
    POSITIVE LOGITS
     coche
    1.79
     trai
    1.71
     κα
    1.67
     riguard
    1.61
     přes
    1.59
     moglie
    1.56
     giorni
    1.55
     presenti
    1.54
     bijvoorbeeld
    1.54
     mesi
    1.53
    Activations Density 0.024%

    No Known Activations