© 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-262K
    7. 115
    Prev
    Next
    INDEX
    Explanations

    steampunk, hermetic, thelema, taiko

    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
    ס
    0.76
    
    0.75
    iş
    0.73
    ipedi
    0.71
    Z
    0.71
    ningen
    0.70
     préférable
    0.70
    ্রাজ
    0.69
    
    0.69
    TimeUnit
    0.68
    POSITIVE LOGITS
     त्यांचे
    0.87
    под
    0.80
    ुक
    0.79
    大
    0.79
    мо
    0.77
    その
    0.77
    altered
    0.75
     verstehen
    0.75
    возможно
    0.75
     змо
    0.73
    Activations Density 0.229%

    No Known Activations