© 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. 30533
    Prev
    Next
    INDEX
    Explanations

    flat tire

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

    The neuron activates on mentions of tire problems—words like “flat,” “blow‐outs,” “puncture,” “burst,” and other terms indicating a deflated or damaged tire.

    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
    progressBar
    -0.71
    inah
    -0.71
     lapar
    -0.71
     hospice
    -0.70
    fifo
    -0.70
     Cock
    -0.70
     ядер
    -0.69
    MBA
    -0.68
     Vag
    -0.67
    
    -0.67
    POSITIVE LOGITS
     puncture
    2.47
     flat
    2.27
     punctures
    2.25
     punctured
    2.16
     flats
    2.03
     tire
    1.95
    flat
    1.90
    Flat
    1.85
     Flat
    1.84
     tyre
    1.81
    Activations Density 0.025%

    No Known Activations