© 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. 10-GEMMASCOPE-RES-131K
    7. 43010
    Prev
    Next
    INDEX
    Explanations

    parking lots and ramps

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

    The main thing this neuron does is detect mentions of parking areas (e.g. parking lots, ramps, garages).

    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
     yoksa
    -1.45
     системой
    -1.44
    jestel
    -1.36
    bable
    -1.27
    ghouse
    -1.17
     necesar
    -1.16
    ناول
    -1.15
    遢
    -1.14
    嚷
    -1.14
    inghouse
    -1.13
    POSITIVE LOGITS
     통해
    1.36
     déterminé
    1.29
    <td>
    1.24
     diamètre
    1.19
     gói
    1.16
    ypeł
    1.13
     як
    1.11
    ⾮
    1.11
     Як
    1.09
     fréquemment
    1.09
    Activations Density 0.037%

    No Known Activations