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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11430
    Prev
    Next
    INDEX
    Explanations

    code keywords and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
    وطه
    0.61
    [{}\
    0.60
     சூழ
    0.59
     minuto
    0.57
     mouseY
    0.56
     सरपंच
    0.55
     hinzu
    0.55
    ě
    0.54
    Ě
    0.54
    🫧
    0.54
    POSITIVE LOGITS
    পাকিস্ত
    0.57
    Thinking
    0.57
    学科
    0.57
     Constitution
    0.57
    罔
    0.56
    Constitution
    0.56
    <h3>
    0.55
     constituting
    0.55
     constitution
    0.55
     constitutes
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.