© 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. 64469
    Prev
    Next
    INDEX
    Explanations

    I think/believe

    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
     kämp
    -1.23
    Sebagai
    -1.12
    förm
    -1.10
     trám
    -1.05
     and
    -1.04
    ürtel
    -1.04
    ⸨
    -1.02
     bekämp
    -1.02
     producir
    -1.00
    Kiedy
    -1.00
    POSITIVE LOGITS
     they
    1.30
     even
    1.16
     vägen
    1.15
     still
    1.14
     fortfarande
    1.13
    还能
    1.05
    no
    1.05
     fortsatt
    1.04
    in
    1.01
     pagal
    1.00
    Activations Density 0.022%

    No Known Activations