© 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. 228780
    Prev
    Next
    INDEX
    Explanations

    Dosage, Dose, Arzneim

    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
    որ
    0.45
    選挙
    0.42
    тно
    0.42
    ESD
    0.42
     sought
    0.41
    引っ
    0.41
    ү
    0.41
    لی
    0.41
    注目
    0.41
    جی
    0.41
    POSITIVE LOGITS
     Dosage
    0.63
     Haram
    0.56
     Meals
    0.55
     Arzneim
    0.54
     Accept
    0.54
     Dose
    0.53
     Harn
    0.53
     Nied
    0.52
     Ecusson
    0.52
     Started
    0.52
    Activations Density 0.000%

    No Known Activations