© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 100763
    Prev
    Next
    INDEX
    Explanations

    garlic, onions, and alliums

    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
     shrubs
    0.46
    QRect
    0.45
     лес
    0.45
    这将
    0.43
     Cessna
    0.42
     скорость
    0.40
    jPanel
    0.40
    序
    0.40
    ⑰
    0.40
    বীন্দ্রনাথ
    0.39
    POSITIVE LOGITS
    🧅
    0.82
     onion
    0.81
     bawang
    0.75
     Onion
    0.71
     onions
    0.71
    onion
    0.66
     bulb
    0.66
     bulbs
    0.64
    Allium
    0.64
    bulb
    0.62
    Activations Density 0.034%

    No Known Activations