© 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. 38389
    Prev
    Next
    INDEX
    Explanations

    240 volts or hours

    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
     tuviera
    -2.56
     estuviera
    -2.27
     ポーチ
    -2.22
    kembangkan
    -2.16
     夜景
    -2.14
    也在
    -2.11
    n
    -2.09
    对他
    -2.06
    譙
    -2.05
     手帳
    -2.03
    POSITIVE LOGITS
    殲
    2.66
    )
    2.50
    𓐍
    2.44
    ⚋
    2.33
    .”
    2.30
     یک
    2.28
     это
    2.27
    橚
    2.27
    𓍊
    2.25
     idée
    2.17
    Activations Density 0.005%

    No Known Activations