© 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. 39417
    Prev
    Next
    INDEX
    Explanations

    areas and measurements

    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
     help
    -1.80
     first
    -1.73
     support
    -1.73
     by
    -1.70
     February
    -1.69
     or
    -1.65
     using
    -1.64
     required
    -1.61
     while
    -1.61
     as
    -1.61
    POSITIVE LOGITS
     vinyle
    1.79
     rayures
    1.67
     plantes
    1.66
     offrir
    1.63
     brune
    1.63
     teint
    1.63
     itinéraires
    1.62
     poulet
    1.61
     envelo
    1.61
     monstre
    1.59
    Activations Density 0.043%

    No Known Activations