© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    languages and countries

    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
    <unused321>
    1.71
    striped
    1.71
    <unused1727>
    1.66
    <unused1604>
    1.61
    <unused1810>
    1.60
    <unused1739>
    1.57
    <unused297>
    1.57
    <unused339>
    1.57
    <unused412>
    1.57
    <unused896>
    1.57
    POSITIVE LOGITS
    /
    1.09
     fraîche
    0.99
    -
    0.98
     respective
    0.95
    zelfde
    0.91
     üzerinden
    0.89
    <b>
    0.87
     berbasis
    0.86
     ad
    0.85
     étudiant
    0.82
    Activations Density 0.009%

    No Known Activations