© 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. 231567
    Prev
    Next
    INDEX
    Explanations

    dining NYC

    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
     அல்லது
    0.61
     或
    0.50
     ወይም
    0.50
     ឬ
    0.48
     partisans
    0.48
     अथवा
    0.48
    (__
    0.47
     или
    0.47
     または
    0.47
     Caedwalla
    0.46
    POSITIVE LOGITS
    dining
    0.46
    NYC
    0.45
    Dining
    0.42
     NYC
    0.41
    ᕐ
    0.41
    વામાં
    0.40
     menit
    0.40
    Pacific
    0.39
     OFFIC
    0.39
    Fecha
    0.39
    Activations Density 0.000%

    No Known Activations