© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37319
    Prev
    Next
    INDEX
    Explanations

    by air or established

    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
     inglés
    0.98
    ’
    0.91
     Bae
    0.90
     B
    0.89
     Dijon
    0.89
     Eileen
    0.88
     árabe
    0.88
     aparecen
    0.88
     egip
    0.88
     Raf
    0.87
    POSITIVE LOGITS
     orifices
    0.86
    ઓને
    0.82
    可以说
    0.82
    pathetic
    0.80
    дать
    0.79
    쬐
    0.79
    ቖ
    0.79
    стина
    0.78
    тия
    0.77
    ો
    0.77
    Activations Density 0.000%

    No Known Activations