© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25564
    Prev
    Next
    INDEX
    Explanations

    parking

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

    parking situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protagon
    0.48
    élève
    0.44
     puiss
    0.44
     Kochubei
    0.44
     plausible
    0.42
     cGraph
    0.42
     ಸಾಮ
    0.42
    梵
    0.42
     sConfig
    0.41
     المؤمن
    0.41
    POSITIVE LOGITS
     Parking
    1.18
     parking
    1.17
    Parking
    1.13
    parking
    1.08
     पार्किंग
    1.02
    停车场
    0.98
    停车
    0.86
    駐車
    0.84
    駐車場
    0.81
     parked
    0.75
    Activations Density 0.080%

    No Known Activations