© 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. 30847
    Prev
    Next
    INDEX
    Explanations

    parking brake

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

    The neuron is detecting terminology tied to uncontrolled vehicle movement or parking‐lock/brake failures (e.g. “rolled away,” “hits,” “truck,” “parking,” “brake,” “lock”).

    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
    PHONY
    -0.81
    Thom
    -0.80
     Thom
    -0.76
     potvr
    -0.75
     zlep
    -0.75
    lios
    -0.73
     recibieron
    -0.72
    kev
    -0.71
    пал
    -0.71
    umbled
    -0.71
    POSITIVE LOGITS
     brakes
    3.45
     brake
    3.33
    brake
    2.83
     Brake
    2.53
    Brake
    2.48
     Brakes
    2.13
    ブレーキ
    1.91
     braking
    1.89
     freno
    1.85
     тормо
    1.80
    Activations Density 0.032%

    No Known Activations