© 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. 64273
    Prev
    Next
    INDEX
    Explanations

    command line usage

    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
     what
    -1.48
     that
    -1.32
     these
    -1.16
     our
    -1.16
     Rät
    -1.06
    createServer
    -1.05
     there
    -1.01
     konden
    -1.00
     this
    -1.00
     Tän
    -1.00
    POSITIVE LOGITS
     ~$
    1.07
     genügend
    1.03
     jedes
    1.02
    发的
    1.02
     gewünschten
    0.99
     propane
    0.98
     to
    0.98
    ⠇
    0.96
     verursacht
    0.95
    荜
    0.95
    Activations Density 0.017%

    No Known Activations