© 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. 8497
    Prev
    Next
    INDEX
    Explanations

    intense focus

    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
    简称
    1.14
     Introduce
    1.04
    Chairman
    1.03
    hereafter
    1.02
    Rep
    1.01
    vgl
    0.99
    ಈ
    0.99
    Fine
    0.99
    whether
    0.97
    Whether
    0.96
    POSITIVE LOGITS
     مهم
    1.11
     bety
    1.04
    <unused2137>
    1.04
    事人
    1.03
     mag
    1.01
     কাব
    0.99
     要
    0.98
     کاز
    0.98
     Институт
    0.95
     legitimately
    0.94
    Activations Density 0.034%

    No Known Activations