© 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. 99365
    Prev
    Next
    INDEX
    Explanations

    vehicle transmissions and gearboxes

    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
     protein
    -0.82
    тивно
    -0.75
    brtc
    -0.75
     วิ
    -0.70
     ब
    -0.69
     أحد
    -0.68
     oben
    -0.68
    雀
    -0.68
    ">.
    -0.67
    المصادر
    -0.67
    POSITIVE LOGITS
     gearbox
    3.45
     transmission
    3.09
     transmissions
    2.72
    transmission
    2.50
    Transmission
    2.34
     Transmission
    2.34
     tranny
    2.17
     TRANSMISSION
    2.03
     transmis
    1.86
    TRANSM
    1.80
    Activations Density 0.052%

    No Known Activations