© 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. 127746
    Prev
    Next
    INDEX
    Explanations

    identifies ability, offers help or capability

    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
     their
    -1.13
     修理
    -1.12
     using
    -1.08
     Kecil
    -1.05
     during
    -0.97
    Makanan
    -0.96
     indicating
    -0.94
    אבל
    -0.92
     restoran
    -0.91
     widespread
    -0.91
    POSITIVE LOGITS
    สามารถ
    1.10
     tools
    1.10
    already
    1.05
     يمكن
    1.02
    ritas
    1.02
     help
    1.01
     offre
    1.00
    ได้
    0.99
    violi
    0.98
     Provides
    0.98
    Activations Density 0.123%

    No Known Activations