© 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. 32692
    Prev
    Next
    INDEX
    Explanations

    configuration files and code

    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
     fhort
    -1.26
     and
    -1.24
    ́i
    -1.23
     blz
    -1.19
     laiss
    -1.19
    ଵ
    -1.18
     asfalto
    -1.16
     lampa
    -1.16
     aéreas
    -1.13
    Transkrypt
    -1.12
    POSITIVE LOGITS
     you
    1.60
     your
    1.55
     exemplo
    1.37
     explicou
    1.31
     conceito
    1.30
     conteúdo
    1.26
    you
    1.22
     detalhe
    1.19
     afirmou
    1.18
     můžete
    1.17
    Activations Density 0.063%

    No Known Activations