© 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. 141684
    Prev
    Next
    INDEX
    Explanations

    dining and meals

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

    dining, dinner, and meals

    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
    탯
    0.46
    केमॉन
    0.44
     skateboard
    0.43
     huid
    0.43
     یو
    0.42
     hike
    0.39
     mağ
    0.39
    bildungs
    0.39
    ابق
    0.38
     hikes
    0.38
    POSITIVE LOGITS
     dining
    1.25
     Dining
    1.24
     diners
    1.22
    Dining
    1.19
    用餐
    1.17
    餐
    1.16
    🍽
    1.14
     Dinner
    1.13
    Dinner
    1.13
     tablecloth
    1.11
    Activations Density 0.183%

    No Known Activations