© 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. 25649
    Prev
    Next
    INDEX
    Explanations

    jazz and related activities

    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
     cuenca
    -0.81
     solvers
    -0.79
     Crying
    -0.76
     earners
    -0.75
     tuve
    -0.75
     rief
    -0.75
     raged
    -0.72
     granja
    -0.72
    rikes
    -0.72
     petri
    -0.71
    POSITIVE LOGITS
     Jaz
    1.09
     hands
    0.96
     Age
    0.94
    Hands
    0.93
     age
    0.92
     AGE
    0.90
     Elle
    0.87
    Age
    0.85
    amata
    0.84
     Hands
    0.84
    Activations Density 0.012%

    No Known Activations