© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 8603
    Prev
    Next
    INDEX
    Explanations

    end-to-end encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يق
    1.34
    لای
    1.30
    ل
    1.30
    ات
    1.25
    джа
    1.17
    لین
    1.13
    SanPham
    1.09
    дри
    1.08
     EBITDA
    1.07
     gerenci
    1.07
    POSITIVE LOGITS
    (
    1.00
     isang
    0.94
    오는
    0.93
     een
    0.89
    습니다
    0.88
     eine
    0.86
    対
    0.86
     dagegen
    0.85
    ための
    0.84
     appelée
    0.84
    Activations Density 0.223%

    No Known Activations