© 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-16K
    7. 13030
    Prev
    Next
    INDEX
    Explanations

    allergy and asthma

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

    allergies and dietary restrictions

    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_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
     deliberation
    0.47
    灣
    0.46
    morale
    0.43
    僵
    0.42
     solvency
    0.42
     stagnation
    0.41
    REGION
    0.41
    getSign
    0.41
    扡
    0.40
    㼛
    0.40
    POSITIVE LOGITS
     allergy
    1.51
     allergen
    1.50
     Allergy
    1.48
     аллер
    1.47
     allerg
    1.46
     allergic
    1.46
     allergens
    1.45
     Allerg
    1.43
     alerg
    1.40
     allergies
    1.38
    Activations Density 0.216%

    No Known Activations