© 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. 205819
    Prev
    Next
    INDEX
    Explanations

    sending back or getting something

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

    unnecessary suffering

    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
    এবং
    0.50
    虛
    0.46
    šnj
    0.43
     Schiller
    0.42
    쇼
    0.42
    補
    0.42
    隂
    0.42
    坫
    0.41
    ः
    0.41
    並且
    0.40
    POSITIVE LOGITS
     फिन
    0.53
     venenatis
    0.52
    roix
    0.50
     ГӀ
    0.48
     něk
    0.47
     jungen
    0.47
     एमसीक्यू
    0.46
     Vivek
    0.46
     yoktur
    0.45
     வண்ணப்பூச்சு
    0.45
    Activations Density 0.000%

    No Known Activations