© 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. 96279
    Prev
    Next
    INDEX
    Explanations

    appendicitis, cholecystitis, tonsils, gallbladder

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

    abdominal pain and appendicitis

    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
     proposto
    0.45
    hando
    0.45
     definido
    0.44
     自
    0.43
     muzzle
    0.42
     SAND
    0.41
    前往
    0.41
     mencionado
    0.41
     establecido
    0.40
     explicado
    0.40
    POSITIVE LOGITS
    avelength
    0.47
    ፣
    0.46
     сезоне
    0.45
     seasonally
    0.44
    ädchen
    0.43
    ituus
    0.43
    シーズン
    0.42
    ştik
    0.41
     ፣
    0.41
     Championships
    0.41
    Activations Density 0.009%

    No Known Activations