© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 250343
    Prev
    Next
    INDEX
    Explanations

    medical conditions or obstructions

    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
    Negative Logits
    ×
    0.47
     Blu
    0.47
     কিন
    0.45
     Puoi
    0.45
     धन
    0.43
    Blu
    0.43
     நடி
    0.42
     тебя
    0.41
    钕
    0.41
     ngươi
    0.40
    POSITIVE LOGITS
    plicates
    0.55
    niers
    0.54
    抱怨
    0.54
    doctors
    0.53
     incompatibility
    0.50
     obstructions
    0.49
     comorbidities
    0.49
     allergens
    0.48
     oiseaux
    0.48
     obstructing
    0.47
    Activations Density 0.000%

    No Known Activations