© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14652
    Prev
    Next
    INDEX
    Explanations

    Customer lookup

    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
    全長
    1.01
     還
    0.94
     また
    0.93
     これ
    0.91
    лимпи
    0.90
     এটাও
    0.90
     действительно
    0.90
     还
    0.86
     واقعی
    0.86
     то
    0.84
    POSITIVE LOGITS
     Moll
    1.21
     Melanie
    1.14
     Melinda
    1.13
     McGuire
    1.09
     cấp
    1.08
     coorden
    1.06
     Muster
    1.06
     கண்காணி
    1.06
     phối
    1.06
    epoca
    1.06
    Activations Density 0.015%

    No Known Activations