© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 37636
    Prev
    Next
    INDEX
    Explanations

    intuitive followed by description

    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
    elijk
    2.30
    ра
    2.14
    会
    2.08
    س
    2.06
    я
    2.05
    nacht
    2.00
    ő
    1.95
    ص
    1.93
    }{
    1.88
    rocessing
    1.82
    POSITIVE LOGITS
    ния
    1.88
    ة
    1.81
     количества
    1.78
    که
    1.72
    istically
    1.62
    banks
    1.61
     Besonders
    1.55
    АС
    1.52
     gráfica
    1.49
    bella
    1.49
    Activations Density 0.004%

    No Known Activations