© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55976
    Prev
    Next
    INDEX
    Explanations

    composite resin fillings

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

    dental materials and terminology related to dental restorations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝜌
    -0.76
    ofos
    -0.75
    eneuve
    -0.75
     phiếu
    -0.73
    ogni
    -0.72
     oversaw
    -0.72
     पानी
    -0.71
     internacionais
    -0.71
    arthed
    -0.70
     vinculados
    -0.70
    POSITIVE LOGITS
     filling
    1.64
    filling
    1.41
     Filling
    1.34
    fills
    1.21
    Filling
    1.20
     fillings
    1.19
    Fill
    1.17
     Fill
    1.13
    FILL
    1.09
     fill
    1.09
    Activations Density 0.070%

    No Known Activations