© 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. 88792
    Prev
    Next
    INDEX
    Explanations

    div class

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

    medical care and treatment

    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
    Method
    0.44
    AKER
    0.42
     câteva
    0.42
    direct
    0.42
    \*
    0.41
    तेक
    0.41
    lefthar
    0.41
    lardan
    0.41
    method
    0.40
    RefItem
    0.40
    POSITIVE LOGITS
     यही
    0.48
    喜
    0.45
     Joyce
    0.44
     Freude
    0.43
    互动
    0.43
     Ново
    0.43
     Annie
    0.42
     Chu
    0.41
     ముఖ్య
    0.41
     Billy
    0.40
    Activations Density 0.000%

    No Known Activations