© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12498
    Prev
    Next
    INDEX
    Explanations

    arthralgia, adenocarcinoma, mesalazine

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

    chemical compounds with "al" endings like "glyoxal", "aldehyde", and "chloral".

    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_10/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
    
    -3.08
    xvii
    -3.02
    铪
    -2.92
    錞
    -2.89
     และ
    -2.88
     ')
    -2.81
    
    -2.77
     asesor
    -2.75
    獁
    -2.73
     แต่
    -2.72
    POSITIVE LOGITS
    1
    3.95
    7
    3.88
    2
    3.88
    er
    3.77
    3
    3.66
    8
    3.53
    H
    3.36
    ized
    3.33
    A
    3.27
    T
    3.25
    Activations Density 0.132%

    No Known Activations