© 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. 143415
    Prev
    Next
    INDEX
    Explanations

    parking and locations

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

    locations follow commas

    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
    ,-
    0.47
     ਜ਼
    0.46
     nghiệp
    0.45
    ".
    0.45
    kun
    0.45
    DAN
    0.43
     banal
    0.43
    french
    0.43
    Ż
    0.43
     ลด
    0.42
    POSITIVE LOGITS
     Parking
    0.53
     parking
    0.48
     locations
    0.46
    場所
    0.45
    場所に
    0.45
    Parking
    0.43
    停车场
    0.42
     místě
    0.42
    箇所
    0.42
     पार्किंग
    0.41
    Activations Density 0.000%

    No Known Activations