© 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. 6742
    Prev
    Next
    INDEX
    Explanations

    x86 assembly instructions

    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
     here
    -1.29
    etzal
    -1.20
    人力
    -1.16
     tiež
    -1.16
     reminds
    -1.13
    žad
    -1.11
    ﷲ
    -1.11
    五百
    -1.11
     this
    -1.10
    },
    -1.10
    POSITIVE LOGITS
    |'.'
    1.14
    生まれる
    1.13
    strnc
    1.13
    Transcrip
    1.12
     estadounid
    1.01
     vinci
    1.00
     zwycię
    0.99
    nachron
    0.98
    Gabriela
    0.98
     zobac
    0.97
    Activations Density 0.061%

    No Known Activations