© 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. 28730
    Prev
    Next
    INDEX
    Explanations

    vomit, spit, phlegm

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

    vomiting and spitting

    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
     لذ
    0.52
    ylmethylsulfanyl
    0.51
    êmement
    0.49
    颧
    0.48
    INCRE
    0.48
     semelhantes
    0.48
    tsó
    0.46
    TPS
    0.45
    increase
    0.45
    वृद्धि
    0.45
    POSITIVE LOGITS
    吐
    0.76
     vomit
    0.62
     regurg
    0.61
     vom
    0.60
    呕
    0.58
     spitting
    0.57
    痰
    0.56
     sputum
    0.55
     Vom
    0.55
     vomiting
    0.54
    Activations Density 0.032%

    No Known Activations