© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92747
    Prev
    Next
    INDEX
    Explanations

    electrical network voltages

    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
    mT
    -0.81
     הספר
    -0.76
    ADOS
    -0.75
    טים
    -0.74
    FQ
    -0.73
     meritorious
    -0.73
    ޑ
    -0.72
    monie
    -0.72
     khởi
    -0.71
     bầu
    -0.71
    POSITIVE LOGITS
     node
    1.12
     voltage
    1.11
     nodal
    1.05
     mesh
    0.99
     branch
    0.99
     voltages
    0.97
    mesh
    0.96
     Mesh
    0.94
     Node
    0.93
     Kirch
    0.91
    Activations Density 0.026%

    No Known Activations