© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8636
    Prev
    Next
    INDEX
    Explanations

    any other

    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
    ERS
    0.84
     січня
    0.78
     грудня
    0.76
     faç
    0.71
     moms
    0.70
    /:
    0.68
     principales
    0.68
    ських
    0.68
     આપવામાં
    0.67
    Email
    0.67
    POSITIVE LOGITS
    тится
    0.78
    󰡔
    0.77
    тический
    0.76
    дию
    0.75
    トゥーン
    0.75
    th
    0.74
    سكر
    0.73
     भव्य
    0.73
    㸽
    0.72
    мы
    0.72
    Activations Density 0.001%

    No Known Activations