© 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. 45367
    Prev
    Next
    INDEX
    Explanations

    HTTP request data

    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
    衛隊
    -0.78
    relsen
    -0.77
     MMP
    -0.75
    ztus
    -0.73
    เท้า
    -0.70
    Precio
    -0.70
     スイーツ
    -0.69
     Vorschläge
    -0.69
     Meteorological
    -0.68
     énergétique
    -0.68
    POSITIVE LOGITS
    timeout
    0.83
     url
    0.80
    url
    0.77
     timeout
    0.75
    精灵
    0.75
     metode
    0.73
    method
    0.72
    ]**
    0.71
     бес
    0.70
    眨
    0.70
    Activations Density 0.010%

    No Known Activations