© 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. 7529
    Prev
    Next
    INDEX
    Explanations

    important considerations and notes

    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
    sia
    1.08
    ా
    1.08
    啊
    1.02
    人了
    1.02
    gia
    0.93
    uggish
    0.93
    ura
    0.92
    Wrong
    0.91
    ش
    0.91
    呀
    0.90
    POSITIVE LOGITS
     ultimately
    1.69
     특히
    1.63
     culminating
    1.62
     vooral
    1.57
     letzt
    1.53
     resulting
    1.52
     wobei
    1.49
     uiteindelijk
    1.49
     emphasizing
    1.48
     eventually
    1.45
    Activations Density 0.214%

    No Known Activations