© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217356
    Prev
    Next
    INDEX
    Explanations

    specific entities and quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    Parkinson's disease tremor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cypress
    0.49
     Publ
    0.47
     NFL
    0.47
     Pineapple
    0.47
     contigo
    0.46
     YouTuber
    0.46
    ：
    0.45
     apaixon
    0.44
    ┑
    0.44
     document
    0.44
    POSITIVE LOGITS
    Ruf
    0.52
    дная
    0.52
    мость
    0.50
    вига
    0.49
    losti
    0.48
    したら
    0.47
    Ruby
    0.46
     минуту
    0.46
     ደቂ
    0.46
    Omega
    0.45
    Activations Density 0.001%

    No Known Activations