© 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. 6699
    Prev
    Next
    INDEX
    Explanations

    input and output operations

    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
     фи
    1.00
     формула
    0.90
     EXHIB
    0.89
     ἐν
    0.87
     специ
    0.87
    镌
    0.87
     Epistle
    0.86
     fáb
    0.86
     whi
    0.86
     е
    0.86
    POSITIVE LOGITS
    更新
    1.13
    reload
    1.06
    ovich
    1.01
    मर्श
    1.00
    nextDouble
    1.00
    ctuations
    0.98
    bewegung
    0.96
    anças
    0.95
     kontroller
    0.95
     Updates
    0.93
    Activations Density 0.011%

    No Known Activations