© 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. 127711
    Prev
    Next
    INDEX
    Explanations

    programming languages and system calls

    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
     all
    -1.46
     well
    -1.28
     small
    -1.26
     over
    -1.17
     four
    -1.16
     on
    -1.16
     which
    -1.16
     three
    -1.14
     significant
    -1.10
     smaller
    -1.10
    POSITIVE LOGITS
     praticamente
    1.27
     témo
    1.18
    もあって
    1.16
     recaudación
    1.16
     verhind
    1.14
    そういった
    1.14
     FORCES
    1.14
     récla
    1.13
    もあるので
    1.13
     véhic
    1.13
    Activations Density 0.040%

    No Known Activations