© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216170
    Prev
    Next
    INDEX
    Explanations

    carrying cases headset

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

    weather balloon context

    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
    Negative Logits
    ur
    0.50
    un
    0.50
    AR
    0.48
     sukar
    0.48
    leton
    0.47
    সর
    0.47
     suffrage
    0.47
    後
    0.46
    泳
    0.45
    ar
    0.45
    POSITIVE LOGITS
     ছাদে
    0.49
    🚣
    0.45
     څرنګوالی
    0.45
     решения
    0.44
    یان
    0.44
     corrects
    0.44
     листь
    0.44
     конф
    0.44
     اجتما
    0.43
    Voids
    0.43
    Activations Density 0.003%

    No Known Activations