© 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. 2334
    Prev
    Next
    INDEX
    Explanations

    what is important

    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
    s
    2.17
    rification
    2.03
     automata
    1.93
    नव
    1.79
    <bos>
    1.78
    aing
    1.76
    ați
    1.73
     automatis
    1.71
     cov
    1.71
     cex
    1.71
    POSITIVE LOGITS
    कांक्षा
    2.23
    𝘢
    2.04
     penting
    2.01
    য়োজনীয়
    1.99
    Importance
    1.98
    ڳ
    1.93
    사항
    1.90
    तमंद
    1.89
    ্লেখ
    1.88
    𝘭
    1.86
    Activations Density 0.508%

    No Known Activations