© 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. 22189
    Prev
    Next
    INDEX
    Explanations

    vomit and sickness

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

    bodily expulsions

    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
    紫外線
    0.46
    izienz
    0.41
    曷
    0.41
    ceğine
    0.40
    िज्म
    0.40
    ৩৯
    0.40
    阳光
    0.40
     말했다
    0.40
     slider
    0.40
     हार
    0.40
    POSITIVE LOGITS
    呕
    0.67
     vomit
    0.65
    嘔
    0.64
     vomiting
    0.63
     venting
    0.63
     gastro
    0.61
     vent
    0.59
     gastric
    0.55
     vom
    0.55
     fecal
    0.55
    Activations Density 0.036%

    No Known Activations