© 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. 4445
    Prev
    Next
    INDEX
    Explanations

    us locations

    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
    YYYY
    1.16
     wurde
    1.03
    Ҥ
    1.00
    subTest
    0.98
     homotopic
    0.98
     wurden
    0.98
     verbess
    0.97
     werde
    0.97
     inició
    0.97
     wird
    0.96
    POSITIVE LOGITS
    <0xA9>
    1.10
    。「
    1.00
     বিনাম
    0.96
     قائد
    0.93
    最有
    0.92
    最具
    0.92
    urato
    0.89
    egger
    0.89
     μεγά
    0.89
    acea
    0.88
    Activations Density 0.018%

    No Known Activations