© 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. 10-GEMMASCOPE-RES-131K
    7. 68617
    Prev
    Next
    INDEX
    Explanations

    political entities and specific names

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     verbess
    -1.15
     encomp
    -1.12
    はこんな感じ
    -1.09
    つも
    -1.07
    стоин
    -1.07
     marshall
    -1.06
    fnptr
    -1.05
     آفت
    -1.04
     Statistica
    -1.04
    一惊
    -1.03
    POSITIVE LOGITS
     there
    1.88
     they
    1.32
    ！
    1.09
    hr
    1.08
     now
    1.04
    bmatrix
    1.04
     为
    1.03
    хим
    1.02
     FOR
    1.02
    bilities
    1.02
    Activations Density 0.407%

    No Known Activations