© 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. 55826
    Prev
    Next
    INDEX
    Explanations

    dates and separators

    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
     much
    -0.89
    ticed
    -0.80
     better
    -0.77
     bezpiecze
    -0.76
     recognizing
    -0.72
     idéia
    -0.71
     umož
    -0.71
    
    -0.71
     nikdy
    -0.69
     presença
    -0.68
    POSITIVE LOGITS
    Whilst
    0.99
     Whilst
    0.94
    başı
    0.91
    scribe
    0.87
    Approximately
    0.84
    ҭ
    0.84
    🥎
    0.82
    yeezy
    0.82
    Artifact
    0.81
     instrumento
    0.80
    Activations Density 0.066%

    No Known Activations