© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9822
    Prev
    Next
    INDEX
    Explanations

    names and descriptive terms

    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
    是不
    1.27
    ৪২
    1.12
     izin
    1.06
    是对
    1.04
    ৯০
    1.04
    冂
    1.03
    乚
    1.03
     minim
    1.03
    𝙞
    1.03
    铁
    1.02
    POSITIVE LOGITS
    otch
    1.09
    लांग
    1.00
    ocalization
    0.99
    acked
    0.99
     discontinuities
    0.99
     snappy
    0.98
    photo
    0.98
    closeup
    0.98
     goofy
    0.97
    oct
    0.97
    Activations Density 0.022%

    No Known Activations