© 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. 146696
    Prev
    Next
    INDEX
    Explanations

    employee spotlights

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

    Social changes, waste, energy, sink

    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
     voor
    0.50
     for
    0.47
    f
    0.47
    สำหรับ
    0.46
     sorular
    0.46
     de
    0.45
     dee
    0.45
    键
    0.44
    寄存
    0.44
     pentru
    0.43
    POSITIVE LOGITS
     Caledonia
    0.48
    izamos
    0.48
    meal
    0.47
    celes
    0.46
     最大
    0.45
    acağı
    0.45
    ozat
    0.44
     পরেও
    0.44
     excess
    0.43
    σα
    0.43
    Activations Density 0.002%

    No Known Activations