© 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-262K
    7. 11265
    Prev
    Next
    INDEX
    Explanations

    Gaussian process or noise

    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_262k_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
     Ở
    1.67
    aks
    1.62
    ต้อง
    1.57
     escuela
    1.52
    oto
    1.49
    pendiente
    1.49
     améric
    1.48
    ได้
    1.47
     vẫn
    1.47
     werde
    1.46
    POSITIVE LOGITS
    د
    2.34
    ل
    1.77
    з
    1.62
    ם
    1.57
    ش
    1.53
    م
    1.47
    ر
    1.45
    ვე
    1.45
    Gaussian
    1.43
    ларда
    1.41
    Activations Density 0.004%

    No Known Activations