© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4186
    Prev
    Next
    INDEX
    Explanations

    carrying or bearing

    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_16k_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
    데
    1.80
    데요
    1.79
    да
    1.78
    ted
    1.74
    ged
    1.71
    кса
    1.69
    忡
    1.66
    ל
    1.66
    ার
    1.64
    monds
    1.63
    POSITIVE LOGITS
     sogenannte
    2.09
    Alla
    2.00
     consigo
    1.99
     ответственности
    1.99
     marít
    1.96
    后果
    1.95
     ответственность
    1.94
    enquête
    1.91
     Año
    1.88
    Agregar
    1.86
    Activations Density 0.232%

    No Known Activations