© 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. 34-GEMMASCOPE-RES-131K
    7. 89915
    Prev
    Next
    INDEX
    Explanations

    Yan-Hu-Suo Corydalis yanhusuo

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

    quotation marks and quoted speech in news articles and academic content.

    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
    Water
    -0.82
    orphic
    -0.79
     RIPRODUZIONE
    -0.79
    }}(
    -0.78
     Water
    -0.78
    ума
    -0.77
     CGSize
    -0.76
    <>(
    -0.75
    posY
    -0.74
    drawImage
    -0.74
    POSITIVE LOGITS
    Lc
    0.86
    ﹟
    0.82
     alojamientos
    0.80
     Kail
    0.77
    attrib
    0.77
     mít
    0.77
    alnya
    0.77
     umož
    0.76
    すべき
    0.75
     píše
    0.75
    Activations Density 0.006%

    No Known Activations