© 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. 223033
    Prev
    Next
    INDEX
    Explanations

    start to, surgery should

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

    diseases and medical terms

    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
    どう
    0.51
     you
    0.43
    ርስዎ
    0.43
     I
    0.42
     afterwards
    0.42
    Years
    0.42
     there
    0.42
    ції
    0.41
    यची
    0.40
    ญ
    0.40
    POSITIVE LOGITS
     초대
    0.51
    웨
    0.49
    ruv
    0.49
    deutscher
    0.48
     инструмента
    0.48
     сал
    0.47
     eszk
    0.47
    诺
    0.46
    orch
    0.46
     факуль
    0.46
    Activations Density 0.001%

    No Known Activations