© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64391
    Prev
    Next
    INDEX
    Explanations

    TODO and FIXME comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    kapital
    -1.00
    𐄁
    -1.00
    Vlastnosti
    -0.99
    嘮
    -0.98
    Cechy
    -0.98
    NhanVien
    -0.97
    UNDA
    -0.97
    ญี่ป
    -0.96
     Öffnen
    -0.96
     мальчика
    -0.96
    POSITIVE LOGITS
     this
    1.15
     including
    1.07
     incluyendo
    1.05
     eventually
    1.02
     hjär
    1.00
     includes
    0.99
     someday
    0.98
     págs
    0.98
    тную
    0.98
     incluye
    0.96
    Activations Density 0.019%

    No Known Activations