© 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. 1167
    Prev
    Next
    INDEX
    Explanations

    forward or reverse gear

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on technical patent–style language describing automatic vehicle transmissions (e.g. “automatic transmission,” “parking lock,” “parking gear,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    keyword
    -0.81
    siones
    -0.80
    chaub
    -0.80
     balloon
    -0.80
    ᵁ
    -0.77
    alagi
    -0.77
    логических
    -0.77
     Simons
    -0.76
    hålla
    -0.75
    balloon
    -0.73
    POSITIVE LOGITS
     gear
    3.39
     gears
    3.08
     Gear
    2.30
    gear
    2.25
     Gears
    2.20
    Gear
    2.20
     GEAR
    1.95
    ギア
    1.94
    Gears
    1.89
    gears
    1.83
    Activations Density 0.025%

    No Known Activations