© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15428
    Prev
    Next
    INDEX
    Explanations

    food, activities, and specific items

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

    food items

    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_16k_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
     
    0.56
    f
    0.51
    ف
    0.47
    liced
    0.46
    lifer
    0.45
    AMS
    0.44
     typical
    0.42
    M
    0.42
    H
    0.42
    TE
    0.42
    POSITIVE LOGITS
     angered
    0.59
    ದಾರ
    0.57
    ữa
    0.56
     εται
    0.55
     বয়সী
    0.54
     रक्षाबंधनाच्या
    0.54
     কোম্প
    0.54
     INDUST
    0.53
     बिज़
    0.53
     nameWithOwner
    0.53
    Activations Density 1.012%

    No Known Activations