© 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. 15395
    Prev
    Next
    INDEX
    Explanations

    parking lot or car park locations

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

    The neuron activates on mentions of parking areas (e.g. “parking lot,” “parking lots,” or similar references).

    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
    “
    -2.13
    咴
    -1.83
     Houſe
    -1.80
    hdysval
    -1.79
    aians
    -1.73
    nommen
    -1.73
     “(
    -1.70
    ”,
    -1.67
    舠
    -1.64
    )}{
    -1.63
    POSITIVE LOGITS
    '
    2.11
    \
    2.05
     of
    1.98
    .'
    1.89
    }
    1.70
     defying
    1.69
    -
    1.66
     adalah
    1.61
    ть
    1.61
    _
    1.57
    Activations Density 0.004%

    No Known Activations