© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3573
    Prev
    Next
    INDEX
    Explanations

    Taiwanese and Asian food dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     పరిస్థి
    0.70
    жета
    0.68
     परिस्थितियों
    0.66
     Tavern
    0.65
    ೂರ್ವ
    0.64
    arian
    0.64
    ử
    0.63
     σημα
    0.62
     Brig
    0.62
    涉及
    0.61
    POSITIVE LOGITS
     taiwan
    0.86
    Taiwan
    0.84
    鉱
    0.81
     Taiwan
    0.81
     wanton
    0.77
     Taiwanese
    0.76
     Bandung
    0.73
     dim
    0.72
    奶
    0.71
     milk
    0.71
    Activations Density 0.076%

    No Known Activations