© 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. 40-GEMMASCOPE-2-RES-65K
    7. 51407
    Prev
    Next
    INDEX
    Explanations

    vestibular balance equilibrium

    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
     macrophage
    0.47
    螯
    0.43
     breast
    0.40
     buck
    0.39
     méth
    0.39
     rende
    0.39
    തം
    0.39
    折り
    0.38
    指
    0.38
    த்தோ
    0.37
    POSITIVE LOGITS
     vestibular
    0.96
     vertigo
    0.95
     dizziness
    0.92
     dizzy
    0.79
     labyr
    0.70
     labyrinth
    0.68
    暈
    0.67
     Vest
    0.64
     vestib
    0.64
    Vest
    0.63
    Activations Density 0.047%

    No Known Activations