© 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. 70244
    Prev
    Next
    INDEX
    Explanations

    power lines and poles

    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
    onz
    -0.88
    istungs
    -0.81
    ("${
    -0.76
    illets
    -0.74
    leding
    -0.73
    Bảo
    -0.73
    मे
    -0.72
    ьер
    -0.71
     波
    -0.71
    rā
    -0.71
    POSITIVE LOGITS
     wires
    2.58
     poles
    2.23
     lines
    2.13
     pole
    2.11
     overhead
    2.03
     wire
    1.87
     transmission
    1.83
    wires
    1.80
     cables
    1.74
     line
    1.66
    Activations Density 0.031%

    No Known Activations