© 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. 33546
    Prev
    Next
    INDEX
    Explanations

    Google Play services connect

    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
     Cello
    -0.90
    awtextra
    -0.80
     kufanya
    -0.76
    ंध
    -0.75
     mentales
    -0.75
     أعلام
    -0.73
     terse
    -0.73
     التص
    -0.72
     فرز
    -0.72
     inco
    -0.71
    POSITIVE LOGITS
     Google
    0.94
    ligible
    0.82
    CONNECTION
    0.82
     Connected
    0.82
    Connection
    0.81
    لاج
    0.80
    oogle
    0.79
     Connection
    0.79
     connected
    0.78
     google
    0.78
    Activations Density 0.011%

    No Known Activations