© 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. 45277
    Prev
    Next
    INDEX
    Explanations

    starting phrases or titles

    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
    JNIEnv
    -0.77
    fels
    -0.73
     truly
    -0.73
    必要な
    -0.71
     preferably
    -0.70
     Envoy
    -0.70
    rungs
    -0.69
    较
    -0.69
     Horacio
    -0.68
     tumble
    -0.67
    POSITIVE LOGITS
    Michigan
    0.87
    mojo
    0.78
     Michigan
    0.78
    箔
    0.76
    createTextNode
    0.72
    openhauer
    0.70
     émer
    0.70
     lamella
    0.70
    PDR
    0.69
     sofa
    0.69
    Activations Density 0.027%

    No Known Activations