© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 139
    Prev
    Next
    INDEX
    Explanations

    he or she

    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_10/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
    datable
    -1.68
    stest
    -1.62
    eable
    -1.61
     industrie
    -1.58
     pamoja
    -1.55
    ompi
    -1.52
     soldat
    -1.50
    lider
    -1.49
    ícias
    -1.47
    rages
    -1.45
    POSITIVE LOGITS
     who
    1.96
     the
    1.82
     this
    1.78
     there
    1.77
     each
    1.67
     only
    1.66
     vinculado
    1.65
     permitirá
    1.64
     described
    1.59
     during
    1.55
    Activations Density 0.117%

    No Known Activations