© 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. 8301
    Prev
    Next
    INDEX
    Explanations

    multiple methods or ways

    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
     but
    2.15
    but
    2.03
    但在
    1.85
    但是
    1.77
    그러나
    1.73
    But
    1.71
    但
    1.71
    但也
    1.70
    BUT
    1.70
    However
    1.69
    POSITIVE LOGITS
     Changer
    1.06
     మాత్రం
    1.01
     Perché
    1.00
     দিবে
    1.00
    タル
    0.99
    setupUi
    0.98
     जाइए
    0.98
     Seja
    0.98
    埬
    0.97
     Bahia
    0.97
    Activations Density 0.294%

    No Known Activations