© 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. 13-GEMMASCOPE-2-RES-16K
    7. 1331
    Prev
    Next
    INDEX
    Explanations

    file extensions and code names

    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
    <unused573>
    1.75
     weaponry
    1.68
    weapons
    1.66
    お金
    1.63
     greenery
    1.63
     firepower
    1.60
     vegetation
    1.58
     wilayah
    1.56
    syair
    1.55
    <unused396>
    1.53
    POSITIVE LOGITS
    ند
    1.26
     Sub
    1.16
     Mini
    1.12
     Super
    1.10
     Stand
    1.04
     Мини
    1.03
     Standard
    1.01
     South
    1.01
     class
    1.01
     Anti
    1.00
    Activations Density 0.105%

    No Known Activations