© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9775
    Prev
    Next
    INDEX
    Explanations

    food and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    жен
    0.45
    铄
    0.43
    ی
    0.41
    underwear
    0.41
    Woman
    0.40
    ços
    0.40
    jó
    0.39
    unoscut
    0.39
    출
    0.38
    രണം
    0.38
    POSITIVE LOGITS
     eaten
    0.80
     food
    0.66
    stuffs
    0.66
     stuffs
    0.65
    truck
    0.64
     Food
    0.62
     truck
    0.61
    🥘
    0.61
     食
    0.61
     cooked
    0.60
    Activations Density 0.015%

    No Known Activations