© 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. 65519
    Prev
    Next
    INDEX
    Explanations

    drive letters and 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
     Vorbereitung
    -0.72
     scuole
    -0.70
     أن
    -0.69
    isei
    -0.69
     slecht
    -0.67
     inició
    -0.67
     journal
    -0.67
    guruan
    -0.66
     ложки
    -0.66
     multiples
    -0.66
    POSITIVE LOGITS
     drive
    2.61
     drives
    2.20
    drive
    2.09
     Drive
    2.03
    Drive
    1.93
     DRIVE
    1.91
    drives
    1.75
    DRIVE
    1.66
     Drives
    1.65
    ドライブ
    1.55
    Activations Density 0.102%

    No Known Activations