© 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. 93857
    Prev
    Next
    INDEX
    Explanations

    opera and dialog interfaces

    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
     deductible
    -0.85
    chestra
    -0.79
    DIRECTIONS
    -0.75
    ργασ
    -0.74
    dedu
    -0.71
     zusammenge
    -0.71
    setVertical
    -0.69
     поколения
    -0.69
     artist
    -0.68
     destinations
    -0.68
    POSITIVE LOGITS
     MessageBoxIcon
    0.86
     opera
    0.83
    опера
    0.82
     operas
    0.81
     Dialog
    0.81
     Laub
    0.81
     Maha
    0.81
     Canti
    0.80
     operar
    0.79
     oper
    0.76
    Activations Density 0.020%

    No Known Activations