© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228675
    Prev
    Next
    INDEX
    Explanations

    numbers and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     পন্থা
    0.47
     நிகழ்ச்சி
    0.46
    ill
    0.45
    の使用
    0.45
    ޔ
    0.45
     Zend
    0.44
     Ide
    0.44
     रूम
    0.44
     تق
    0.43
     本当
    0.43
    POSITIVE LOGITS
     komplex
    0.46
     papier
    0.42
     starost
    0.42
    糠
    0.41
     investimentos
    0.40
    铵
    0.40
    盐
    0.40
    公司
    0.40
     compleja
    0.40
    লগ্ন
    0.40
    Activations Density 0.001%

    No Known Activations