© 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. 31-GEMMASCOPE-2-RES-65K
    7. 62523
    Prev
    Next
    INDEX
    Explanations

    horsesequinepink skin

    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_31_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
     cattle
    0.47
    cattle
    0.44
    哞
    0.44
    嵯
    0.43
    牦
    0.43
     rodeo
    0.42
     vaca
    0.42
     шер
    0.41
    aurus
    0.41
     horns
    0.41
    POSITIVE LOGITS
     Equ
    0.43
     bituminous
    0.41
     핵
    0.41
     fungal
    0.40
     equine
    0.39
    horse
    0.39
     equ
    0.38
     Horse
    0.38
     horse
    0.38
     रखी
    0.37
    Activations Density 0.025%

    No Known Activations