© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 228780
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    որ
    0.41
     sought
    0.41
    тно
    0.41
    通り
    0.40
    ү
    0.40
    引っ
    0.39
    려는
    0.39
    рт
    0.39
    次元
    0.39
    選挙
    0.38
    POSITIVE LOGITS
     Meals
    0.57
     Dosage
    0.55
    STARTED
    0.54
     Haram
    0.54
     Accept
    0.53
     পদ্ধ
    0.52
     Ecusson
    0.50
    eating
    0.50
     Estable
    0.50
     Depends
    0.49
    Activations Density 0.009%

    No Known Activations