© 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. 12345
    Prev
    Next
    INDEX
    Explanations

    cooking times

    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
     alakalı
    1.31
     ilgili
    1.29
    自分
    1.25
    햐
    1.24
    𝙞
    1.20
     кантип
    1.19
     insanların
    1.18
    ಈ
    1.18
    例如
    1.17
     belirli
    1.17
    POSITIVE LOGITS
     .
    0.96
     +
    0.95
     --
    0.93
     B
    0.90
     (
    0.90
     ;
    0.89
     —
    0.88
     *
    0.88
     NE
    0.88
     Ach
    0.85
    Activations Density 0.062%

    No Known Activations