© 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. 49524
    Prev
    Next
    INDEX
    Explanations

    excavators and construction equipment

    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
     Gers
    -0.84
    ін
    -0.82
    leiding
    -0.78
     herds
    -0.78
    牛仔
    -0.77
    ējās
    -0.77
    axle
    -0.75
     nargin
    -0.73
     पढ़
    -0.72
     niggas
    -0.71
    POSITIVE LOGITS
     excavator
    1.11
     excav
    1.04
     Exca
    1.01
     mini
    0.96
     midi
    0.88
    mini
    0.88
    Mini
    0.87
    넥
    0.81
     Kimmel
    0.79
    Calculator
    0.79
    Activations Density 0.016%

    No Known Activations