© 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
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14210
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h4>
    0.94
    <h4>
    0.84
     view
    0.67
    View
    0.62
     просмо
    0.61
    view
    0.60
    ”;
    0.59
    closes
    0.58
    VIEW
    0.57
     بررسی
    0.57
    POSITIVE LOGITS
     About
    0.85
     Copyright
    0.77
     अबाउट
    0.76
     ABOUT
    0.75
     ©
    0.66
     McGraw
    0.66
    About
    0.65
     copyright
    0.61
     عنها
    0.61
    ခ
    0.61
    Activations Density 0.000%

    No Known Activations