© 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. 15514
    Prev
    Next
    INDEX
    Explanations

    Slow

    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
    не
    2.14
    sthe
    1.91
    d
    1.81
    l
    1.77
    alogical
    1.71
    ৩৬
    1.70
    stances
    1.68
    itt
    1.65
    ['
    1.64
    speople
    1.63
    POSITIVE LOGITS
    ق
    2.70
    م
    2.50
    ف
    2.50
    ه
    2.39
    та
    2.27
    ا
    2.16
    های
    1.77
    هر
    1.77
     οπο
    1.70
    هي
    1.70
    Activations Density 0.061%

    No Known Activations