© 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. 235584
    Prev
    Next
    INDEX
    Explanations

    categories and events

    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
    به
    0.54
    نا
    0.50
    Voor
    0.49
    وضع
    0.49
    美丽的
    0.48
    ق
    0.47
    مان
    0.47
    Пред
    0.46
    𝑭
    0.46
    В
    0.46
    POSITIVE LOGITS
    }')
    0.50
     artery
    0.50
     sculpture
    0.50
     গাঁ
    0.46
     contradict
    0.46
    のア
    0.46
     circling
    0.46
     Gothic
    0.46
     leafy
    0.46
     sculptures
    0.45
    Activations Density 0.000%

    No Known Activations