© 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. 119152
    Prev
    Next
    INDEX
    Explanations

    high risk, high glucose, high grade

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

    phrases containing the word "high" followed by medical or scientific terms.

    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
     ограничения
    -0.81
    缓
    -0.78
    サッカー
    -0.75
     shim
    -0.73
    orre
    -0.72
    autorisation
    -0.72
     underv
    -0.72
     Myra
    -0.71
    ourt
    -0.71
    轭
    -0.70
    POSITIVE LOGITS
     برخ
    0.82
     hoj
    0.76
    ecio
    0.75
    CoA
    0.74
    باح
    0.74
    beho
    0.74
     eivät
    0.73
    racite
    0.73
    いち
    0.71
    folge
    0.67
    Activations Density 0.118%

    No Known Activations