© 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. 208632
    Prev
    Next
    INDEX
    Explanations

    leafy greens and spinach

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

    palak paneer

    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
    🍭
    0.50
    🥭
    0.48
    🥥
    0.47
    껍
    0.46
    Hawaii
    0.46
    🍊
    0.45
    carousel
    0.44
     ઓફ
    0.44
    hamming
    0.43
    🍐
    0.43
    POSITIVE LOGITS
     greens
    0.71
     Lettuce
    0.66
     salads
    0.64
     chlorophyll
    0.61
    🥬
    0.60
     Spinach
    0.59
     Greens
    0.58
     leafy
    0.57
     lettuce
    0.56
     Chlor
    0.55
    Activations Density 0.112%

    No Known Activations