© 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. 22-GEMMASCOPE-RES-131K
    7. 411
    Prev
    Next
    INDEX
    Explanations

    ul and ulcer

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

    HTML elements such as 'ul' (unordered list) tags and medical terms related to ulcers.

    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_22/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
     แต่
    -3.19
     But
    -3.11
    贗
    -2.41
    pecabe
    -2.39
     You
    -2.22
    ",
    -2.14
     ſont
    -2.14
    
    -2.06
    ),
    -2.05
    ついで
    -2.05
    POSITIVE LOGITS
     begun
    2.69
    𓆜
    2.63
    етки
    2.44
    ኾ
    2.27
    
    2.23
    ?"
    2.22
    етка
    2.22
    …?
    2.20
    та
    2.16
    鷓
    2.13
    Activations Density 0.009%

    No Known Activations