© 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. 158726
    Prev
    Next
    INDEX
    Explanations

    facilitate change

    np_acts-logits-general · gemini-2.5-flash-lite

    need or opportunity

    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
     सौंपी
    0.53
     তোলা
    0.51
    薯
    0.50
    কেলে
    0.49
     Shrimp
    0.48
     வண்ணப்பூச்சு
    0.47
     விஜய்
    0.47
     ভী
    0.47
     வண்ண
    0.46
     Sticker
    0.46
    POSITIVE LOGITS
    '
    0.58
     fram
    0.54
     of
    0.54
    .
    0.53
     trad
    0.53
     avenues
    0.50
     urbanization
    0.50
     uses
    0.49
     fem
    0.49
     due
    0.48
    Activations Density 0.001%

    No Known Activations