© 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. 10286
    Prev
    Next
    INDEX
    Explanations

    game setup

    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
     *>(
    0.76
     !",
    0.69
     ('
    0.68
    साब
    0.68
     '');
    0.68
     DECEMBER
    0.66
     presentations
    0.65
    .'.
    0.65
     पाण्यात
    0.65
     কৰি
    0.64
    POSITIVE LOGITS
    en
    1.02
    зать
    0.89
    た
    0.86
     chứa
    0.86
     causas
    0.85
     sáb
    0.84
    ತಾ
    0.84
     Galileo
    0.84
     Gasp
    0.84
    ﺔ
    0.84
    Activations Density 0.000%

    No Known Activations