© 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. 34-GEMMASCOPE-RES-131K
    7. 25985
    Prev
    Next
    INDEX
    Explanations

    names preceded by age or relation

    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_34/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
    Margot
    -1.20
     Margot
    -1.00
    Harriet
    -0.95
     Galapagos
    -0.88
     ApiClient
    -0.87
     sophie
    -0.84
    Elsa
    -0.84
    velg
    -0.84
    Mimi
    -0.84
    Betsy
    -0.82
    POSITIVE LOGITS
     Cody
    1.78
     Tyler
    1.69
     Brandon
    1.55
     Travis
    1.54
     Ashley
    1.53
     Joshua
    1.46
     Dakota
    1.45
     Jordan
    1.41
     Austin
    1.41
    Cody
    1.41
    Activations Density 0.086%

    No Known Activations