© 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. 167792
    Prev
    Next
    INDEX
    Explanations

    global ocean

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

    often dismissed or misunderstood

    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
    ມີ
    0.53
     테스트
    0.48
    ポンプ
    0.46
    랗
    0.45
    าม
    0.45
    셔
    0.45
    ドラゴン
    0.45
    름
    0.44
     собаки
    0.44
     타입
    0.44
    POSITIVE LOGITS
     sourced
    0.58
     funding
    0.54
     funded
    0.54
     newsletter
    0.54
     final
    0.53
     landfill
    0.51
     cache
    0.50
     antidepressant
    0.50
     DVD
    0.50
     diary
    0.49
    Activations Density 0.001%

    No Known Activations