© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1260
    Prev
    Next
    INDEX
    Explanations

    dental restorations and treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
    мії
    0.40
     архівної
    0.40
    сіі
    0.39
    瞞
    0.36
     pubblici
    0.36
    驃
    0.36
    НІ
    0.36
    ShoppingCart
    0.36
    靗
    0.36
     στις
    0.35
    POSITIVE LOGITS
     tooth
    0.52
     dentist
    0.52
     dental
    0.52
     porcelain
    0.52
     dentists
    0.52
     resin
    0.48
     harmonious
    0.48
     teeth
    0.48
     veneer
    0.48
     restorations
    0.48
    Activations Density 0.008%

    No Known Activations