© 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. 12106
    Prev
    Next
    INDEX
    Explanations

    relaxation and relaxed muscles

    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
    ‌ای
    1.87
    ו
    1.83
    ς
    1.81
    ्स
    1.79
    s
    1.77
    وو
    1.73
    یا
    1.71
    ра
    1.70
    ات
    1.70
    ய
    1.70
    POSITIVE LOGITS
    ことにより
    1.94
    thirds
    1.86
     thiểu
    1.84
    rencies
    1.78
    ভাবে
    1.77
    storms
    1.64
    setRequestHeader
    1.63
     Needless
    1.60
     prothorax
    1.59
     hugely
    1.59
    Activations Density 0.070%

    No Known Activations