© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4795
    Prev
    Next
    INDEX
    Explanations

    calm, soothing, or relaxing states

    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
    Waar
    1.67
    রিদ্র
    1.51
     conifers
    1.48
    Хо
    1.43
    ಕ
    1.42
     המ
    1.41
    nez
    1.41
    Ά
    1.40
    ৪৯
    1.38
    Hej
    1.38
    POSITIVE LOGITS
    у
    1.87
    ants
    1.55
     quyển
    1.54
    ui
    1.52
    ándose
    1.51
    ್‌
    1.51
    uate
    1.45
    وْ
    1.44
    )"))
    1.43
     nhàng
    1.43
    Activations Density 0.283%

    No Known Activations