© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10885
    Prev
    Next
    INDEX
    Explanations

    digestive system and its issues

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

    digestive system and stomach lining

    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_40_width_16k_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
    Tennis
    0.51
     vamp
    0.50
     pian
    0.44
    钢琴
    0.44
    鬓
    0.43
    ピアノ
    0.43
     Tennis
    0.42
     Pian
    0.42
     tenis
    0.42
    บคุม
    0.42
    POSITIVE LOGITS
     digestive
    2.06
     intestinal
    2.05
     gastro
    1.93
     gastroenter
    1.92
    胃
    1.89
    腸
    1.89
    消化
    1.85
     intestin
    1.85
     Digestive
    1.84
    肠
    1.80
    Activations Density 0.331%

    No Known Activations