© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    cable, jacket, shield, strain

    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
    overflow
    -0.79
    lysses
    -0.78
    
    -0.77
    IEVE
    -0.75
    เซ
    -0.74
    abank
    -0.74
    Overflow
    -0.72
    što
    -0.71
    nagar
    -0.70
    battery
    -0.69
    POSITIVE LOGITS
     jacket
    1.18
     shield
    1.07
     Shield
    1.03
    shield
    1.00
     shielding
    0.96
     jackets
    0.95
    Shield
    0.93
     strain
    0.93
     Jacket
    0.92
    Jacket
    0.91
    Activations Density 0.041%

    No Known Activations