© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28185
    Prev
    Next
    INDEX
    Explanations

    SQL column definitions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -1.73
     because
    -1.58
     just
    -1.41
     either
    -1.36
     that
    -1.36
     also
    -1.33
     only
    -1.30
     all
    -1.30
     by
    -1.26
     this
    -1.23
    POSITIVE LOGITS
     empêcher
    1.47
     necesarios
    1.41
     prioridad
    1.30
     terminer
    1.30
     faciliter
    1.25
     bloquer
    1.23
     souvent
    1.23
    isir
    1.21
     Atención
    1.20
     indiquer
    1.17
    Activations Density 0.032%

    No Known Activations