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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 28204
    Prev
    Next
    INDEX
    Explanations

    vegetables and fruits

    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_31_width_65k_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
    渔
    0.48
     autent
    0.48
     milit
    0.47
     militias
    0.46
     military
    0.44
     securities
    0.43
     nanop
    0.43
    ديث
    0.43
     authentic
    0.42
    მასრულ
    0.42
    POSITIVE LOGITS
    蔬菜
    1.00
     zucchini
    0.89
    🍅
    0.89
    🥔
    0.87
     vegetable
    0.86
     vegetables
    0.85
     Vegetables
    0.85
    野菜
    0.85
     Tomatoes
    0.83
    🥕
    0.82
    Activations Density 0.241%

    No Known Activations