© 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. 65183
    Prev
    Next
    INDEX
    Explanations

    automotive brake systems

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

    The neuron strongly activates on occurrences of “brake” (and related mechanical braking terms), effectively detecting mentions of brake components or brake systems.

    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
     топли
    -0.96
    minated
    -0.92
     meto
    -0.85
    絎
    -0.84
     pasteles
    -0.80
    atika
    -0.77
    -------
    -0.76
     the
    -0.76
    outros
    -0.76
     می‌گو
    -0.75
    POSITIVE LOGITS
     system
    2.05
    system
    1.27
    系統
    1.16
     System
    1.13
     systems
    1.05
    系统的
    1.03
    SYSTEM
    1.02
    系统
    0.97
     mechanism
    0.93
     系统
    0.92
    Activations Density 0.060%

    No Known Activations