© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31950
    Prev
    Next
    INDEX
    Explanations

    JBL headphones wireless

    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
     footwear
    -0.76
    ウダー
    -0.75
    鞋
    -0.73
    ब्द
    -0.72
    ชี
    -0.71
    etchup
    -0.71
     blanca
    -0.71
    を抜
    -0.71
     dolores
    -0.69
    阵法
    -0.69
    POSITIVE LOGITS
     ANC
    1.06
     wireless
    0.99
     Bluetooth
    0.98
     Wireless
    0.98
    BT
    0.97
     over
    0.94
     headphones
    0.92
     overhead
    0.90
     OVER
    0.87
     cans
    0.85
    Activations Density 0.016%

    No Known Activations