© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6394
    Prev
    Next
    INDEX
    Explanations

    nuts and produce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     bowl
    0.66
     monolayer
    0.59
     गेंदबाजी
    0.57
     internship
    0.57
     chromatographic
    0.57
     smelting
    0.57
     옷
    0.56
     Bowl
    0.56
    鎧
    0.56
     looms
    0.55
    POSITIVE LOGITS
     avocados
    1.32
     potatoes
    1.30
     almonds
    1.30
     tomatoes
    1.24
     bananas
    1.23
     onions
    1.19
     hazelnuts
    1.19
     carrots
    1.18
     blueberries
    1.15
     strawberries
    1.14
    Activations Density 0.501%

    No Known Activations