© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1557
    Prev
    Next
    INDEX
    Explanations

    miniature worlds, other universes

    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_17_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
     lathe
    0.97
     dplyr
    0.90
     maxillary
    0.85
     casework
    0.85
    rut
    0.82
     peroneal
    0.82
     acet
    0.81
    呱
    0.80
     Nev
    0.79
     typography
    0.78
    POSITIVE LOGITS
     billion
    2.79
    billion
    2.74
     Milliarden
    2.68
     Billion
    2.66
     billions
    2.62
     bilhões
    2.50
     миллиар
    2.46
     miliardi
    2.41
     milliards
    2.41
     млрд
    2.23
    Activations Density 0.286%

    No Known Activations