© 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. 87231
    Prev
    Next
    INDEX
    Explanations

    construction equipment, machinery, or parts

    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
     pastoral
    -0.84
    Antenna
    -0.80
     RACE
    -0.78
     गर्न
    -0.73
    গ্র
    -0.72
     couche
    -0.71
    PARSER
    -0.69
     phenyl
    -0.68
    flas
    -0.68
     nut
    -0.68
    POSITIVE LOGITS
     моби
    1.04
     diesel
    0.96
     portable
    0.95
     mobile
    0.95
    mobile
    0.92
    rental
    0.90
     Rental
    0.88
    anlage
    0.83
    Rental
    0.80
    MOBILE
    0.80
    Activations Density 0.022%

    No Known Activations