© 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. 3880
    Prev
    Next
    INDEX
    Explanations

    dialogue opening phrases

    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
    （
    0.99
     (
    0.96
     "
    0.93
     in
    0.93
     discretionary
    0.82
     「
    0.82
     करण्यासाठी
    0.81
    ناسب
    0.79
     increases
    0.77
     encapsulates
    0.77
    POSITIVE LOGITS
     дочь
    1.06
     जेई
    0.97
     дочери
    0.97
     filha
    0.96
    ໋
    0.96
    !”.
    0.93
     ragazza
    0.91
     biología
    0.91
     niña
    0.90
    !`
    0.89
    Activations Density 0.579%

    No Known Activations