© 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. 31-GEMMASCOPE-2-RES-65K
    7. 8502
    Prev
    Next
    INDEX
    Explanations

    yogurt, milk, and dairy

    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
     अग्न
    0.45
    蜚
    0.44
     이해
    0.41
     одежда
    0.41
     เด่น
    0.41
     юк
    0.41
     листь
    0.41
     стрель
    0.41
     насеко
    0.40
    闽
    0.40
    POSITIVE LOGITS
     creamy
    1.05
     milk
    0.98
     Cream
    0.97
     dairy
    0.96
     cream
    0.95
     Dairy
    0.94
    Cream
    0.94
    Dairy
    0.92
     sữa
    0.91
    Milk
    0.91
    Activations Density 0.232%

    No Known Activations