© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11050
    Prev
    Next
    INDEX
    Explanations

    to

    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_24_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
    andering
    0.47
    選擇
    0.46
     선택
    0.45
    ﺒ
    0.43
    选择
    0.43
    ուս
    0.42
     Kết
    0.41
     选择
    0.40
     결과를
    0.39
    ﺘ
    0.39
    POSITIVE LOGITS
     אבל
    0.50
     vanwege
    0.48
     preceding
    0.46
     chez
    0.44
     pero
    0.42
     mutta
    0.41
     kerana
    0.41
     maestra
    0.41
     eigentlich
    0.40
     auspices
    0.40
    Activations Density 0.031%

    No Known Activations