© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 779
    Prev
    Next
    INDEX
    Explanations

    horse related terms

    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
     cysteine
    0.82
     tomat
    0.76
    🍕
    0.75
    잎
    0.74
     rétr
    0.73
     atomically
    0.73
     tomate
    0.72
    邹
    0.71
    🍙
    0.71
    Arduino
    0.71
    POSITIVE LOGITS
     horse
    2.91
     horses
    2.88
     equine
    2.63
     Horses
    2.54
    Horse
    2.53
     Horse
    2.51
    horse
    2.42
     caballos
    2.32
    🐴
    2.29
     stallion
    2.26
    Activations Density 0.368%

    No Known Activations