© 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. 10-GEMMASCOPE-RES-131K
    7. 67932
    Prev
    Next
    INDEX
    Explanations

    vehicle

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

    The neuron is highly activated by mentions of “vehicle” or “vehicles,” effectively detecting references to motor vehicles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ."
    -2.92
    which
    -2.73
    硨
    -2.70
    s
    -2.39
     vitale
    -2.20
    est
    -2.20
    “
    -2.11
     maît
    -2.09
    }{
    -2.03
    ].
    -2.03
    POSITIVE LOGITS
     Their
    2.64
    轱
    2.64
    増えて
    2.59
     proteger
    2.56
    傷害
    2.52
     afectada
    2.50
     kurzen
    2.42
     speziellen
    2.36
    ſelf
    2.33
     {
    2.31
    Activations Density 0.018%

    No Known Activations