© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50055
    Prev
    Next
    INDEX
    Explanations

    goat, goats

    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_40_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
    牛
    0.40
     насеко
    0.39
    牛肉
    0.39
     అధికారులు
    0.38
    zenes
    0.37
    ℡
    0.36
    垓
    0.36
    èges
    0.36
    阪
    0.36
     Vogel
    0.35
    POSITIVE LOGITS
     goat
    1.78
     goats
    1.70
     Goat
    1.70
    🐐
    1.48
    goat
    1.48
     बकरी
    1.22
    羊
    1.07
     Sheep
    0.94
    Sheep
    0.92
     sheep
    0.91
    Activations Density 0.029%

    No Known Activations