© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 31722
    Prev
    Next
    INDEX
    Explanations

    Yukon Gold potatoes

    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_all/layer_41_width_262k_l0_big
    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
     ইসলামিক
    0.37
     windshield
    0.36
    acing
    0.35
    蛛
    0.35
     loops
    0.34
     Embar
    0.34
     compr
    0.34
     bows
    0.34
     headband
    0.34
     burung
    0.34
    POSITIVE LOGITS
     potatoes
    1.76
     Potatoes
    1.66
     potato
    1.64
     Potato
    1.55
    Potato
    1.51
    potato
    1.44
    🥔
    1.42
     आलू
    1.30
    薯
    1.07
     আলু
    1.03
    Activations Density 0.012%

    No Known Activations