© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    are your/their/they

    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
    ាញ
    2.60
    ႇ
    2.46
     entraîne
    2.45
     definición
    2.44
    麽
    2.40
    فيق
    2.39
    माने
    2.39
    っぱり
    2.39
    啼
    2.38
    त्रेयी
    2.38
    POSITIVE LOGITS
    ization
    2.03
    िक
    1.89
    ђа
    1.85
    닷
    1.80
    ">{
    1.78
     mound
    1.73
     building
    1.72
     dioxide
    1.71
    aceous
    1.71
    鹉
    1.69
    Activations Density 0.329%

    No Known Activations