© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9049
    Prev
    Next
    INDEX
    Explanations

    slowness or delay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    MAG
    0.59
    ANN
    0.57
    ذور
    0.55
    Ỗ
    0.54
    DIRECTION
    0.52
    र्निंग
    0.51
     маг
    0.50
    льной
    0.50
    ု
    0.50
    magnet
    0.50
    POSITIVE LOGITS
     late
    3.19
     Late
    2.91
    Late
    2.81
    late
    2.77
    遅
    2.73
     delayed
    2.69
    늦
    2.69
     belated
    2.61
     tard
    2.45
    delayed
    2.45
    Activations Density 0.457%

    No Known Activations