© 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. 127718
    Prev
    Next
    INDEX
    Explanations

    group management and actions

    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
     kosme
    -1.45
     délicieux
    -1.41
     lindos
    -1.37
     keram
    -1.32
     emballage
    -1.30
     klienta
    -1.30
     incrí
    -1.30
     internetu
    -1.28
     linge
    -1.28
     ujar
    -1.27
    POSITIVE LOGITS
     done
    1.24
    R
    1.20
    get
    1.16
    n
    1.13
     set
    1.12
     update
    1.09
    </em>
    1.08
     re
    1.06
    f
    1.06
    였
    1.03
    Activations Density 0.020%

    No Known Activations