© 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. 34-GEMMASCOPE-RES-131K
    4. 109619
    Prev
    Next
    INDEX
    Explanations

    code comments and file paths

    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
     nail
    -0.77
    Buy
    -0.76
    baking
    -0.69
    osy
    -0.68
     touristes
    -0.68
     Tisch
    -0.67
     hitting
    -0.67
    kauft
    -0.66
     tivesse
    -0.66
    Count
    -0.66
    POSITIVE LOGITS
     STEAM
    0.73
    綫
    0.70
    
    0.70
     optima
    0.69
     quello
    0.68
    omethane
    0.68
    entrion
    0.67
     imperme
    0.66
     mediterranean
    0.66
     Snapshot
    0.66
    Activations Density 0.071%

    No Known Activations