© 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. 207063
    Prev
    Next
    INDEX
    Explanations

    city Palaces

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

    completely, always, just

    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
     gols
    0.56
    inology
    0.47
    این
    0.47
     policial
    0.46
    avent
    0.46
    countries
    0.45
    ن
    0.45
    いました
    0.45
     ço
    0.45
    empor
    0.45
    POSITIVE LOGITS
     カー
    0.42
     Californian
    0.40
     連
    0.40
    䨋
    0.40
    喉
    0.39
     洗
    0.39
    璁
    0.39
    沸
    0.38
    锥
    0.38
     উদ্বেগ
    0.38
    Activations Density 0.001%

    No Known Activations