© 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. 4852
    Prev
    Next
    INDEX
    Explanations

    flask api or jokes

    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
     حالا
    0.86
     alias
    0.82
    ijs
    0.82
     miserable
    0.82
     (£
    0.81
     woe
    0.78
     almighty
    0.76
     wretched
    0.76
     blissful
    0.76
    #[
    0.75
    POSITIVE LOGITS
    亣
    1.77
     innych
    1.76
    䧉
    1.75
     budaya
    1.73
    爣
    1.73
     kulttu
    1.71
    㞱
    1.70
     культуры
    1.70
    㹂
    1.69
    埛
    1.67
    Activations Density 0.002%

    No Known Activations