© 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. 6081
    Prev
    Next
    INDEX
    Explanations

    batch file echo off

    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
     povinn
    1.19
     Web
    1.14
     её
    1.12
     n
    1.10
     MORE
    1.08
     учё
    1.06
     web
    1.05
     всё
    1.05
     injust
    1.04
    n
    1.03
    POSITIVE LOGITS
     Derbyshire
    1.49
     Gloucestershire
    1.40
    ര്‍
    1.35
     Northumberland
    1.33
     Watercolour
    1.33
     videomuzda
    1.31
     Traveller
    1.30
     characterised
    1.30
     Shropshire
    1.29
     ductility
    1.29
    Activations Density 0.002%

    No Known Activations