© 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. 94059
    Prev
    Next
    INDEX
    Explanations

    platform device.h

    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
     losses
    -0.75
    itone
    -0.74
     användas
    -0.73
    itivo
    -0.73
     Lieblings
    -0.71
    akaran
    -0.71
    限り
    -0.71
     invokevirtual
    -0.71
     ljud
    -0.71
    bur
    -0.70
    POSITIVE LOGITS
     browser
    0.99
    browser
    0.98
    Browser
    0.95
     Browser
    0.94
    Sao
    0.83
     تاريخ
    0.82
    gluten
    0.82
     Vee
    0.81
     PAGE
    0.80
    ورن
    0.75
    Activations Density 0.002%

    No Known Activations