© 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. 123909
    Prev
    Next
    INDEX
    Explanations

    erythropoietin or et words

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

    scientific and technical terms, particularly in biochemistry and technology, that end with 'et' or 'in'.

    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
    舠
    -3.13
    趼
    -2.55
    a
    -2.36
    鐿
    -2.34
    窨
    -2.17
     podstawie
    -2.14
    e
    -2.13
    鈊
    -2.08
    闿
    -2.08
    ०
    -2.08
    POSITIVE LOGITS
    eacute
    2.52
    ка
    2.36
    rozco
    2.23
    телям
    2.23
    ongiorno
    2.20
     нова
    2.20
     България
    2.17
    to
    2.16
    可以
    2.13
    不算
    2.11
    Activations Density 0.048%

    No Known Activations