© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15526
    Prev
    Next
    INDEX
    Explanations

    sentence processing instructions

    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
    aluronic
    1.22
     Тол
    1.20
     hoạt
    1.13
     oksid
    1.12
     ruthenium
    1.12
     ಭಾರ
    1.12
    ból
    1.10
    >|</
    1.10
     Büyük
    1.09
    ៉ុ
    1.09
    POSITIVE LOGITS
    <blockquote>
    1.02
    urch
    0.90
     three
    0.84
     еще
    0.84
     against
    0.83
    消費者
    0.83
    izer
    0.82
     deux
    0.82
     even
    0.82
    acha
    0.81
    Activations Density 0.009%

    No Known Activations