© 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. 49825
    Prev
    Next
    INDEX
    Explanations

    speed and urgency

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

    The neuron fires on occurrences of the substring “fast” (e.g. in module names, URLs, product or paper titles, class names, 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
    ゙
    -0.75
     zuständig
    -0.72
    lería
    -0.71
    mell
    -0.71
    américa
    -0.70
     INF
    -0.70
     حدث
    -0.70
    世的
    -0.70
     כאשר
    -0.70
    ów
    -0.69
    POSITIVE LOGITS
     Fast
    0.90
    Faster
    0.89
     Urgent
    0.86
     Faster
    0.83
     Accelerated
    0.82
    Practices
    0.80
     لا
    0.80
    delige
    0.80
    Primero
    0.78
     urgente
    0.75
    Activations Density 0.045%

    No Known Activations