© 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. 8504
    Prev
    Next
    INDEX
    Explanations

    quick followed by time estimates

    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
    فر
    1.03
    FC
    1.02
     [
    1.01
     CQG
    0.99
    Comm
    0.95
     https
    0.95
    https
    0.95
    𝖎
    0.93
     #
    0.93
     ‪
    0.93
    POSITIVE LOGITS
    哚
    1.28
    ccncc
    1.20
    iativa
    1.12
    ним
    1.09
    ⃘
    1.08
    ẩ
    1.06
    кара
    1.06
    лган
    1.05
    тил
    1.05
    arza
    1.03
    Activations Density 0.003%

    No Known Activations