© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39708
    Prev
    Next
    INDEX
    Explanations

    Conway, epitopes, Boyd

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

    proper names and technical terms like "Conway," "Grosvenor," and "epitopes."

    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
    禤
    -2.89
    H
    -2.78
    B
    -2.63
    K
    -2.61
     москве
    -2.53
    2
    -2.52
    Z
    -2.44
    鸶
    -2.41
    X
    -2.41
     związane
    -2.39
    POSITIVE LOGITS
    </h3>
    3.42
    ).
    3.41
    </i>
    2.91
    '
    2.84
    "
    2.66
    」「
    2.61
     When
    2.55
    ࿆
    2.38
    ';
    2.28
    ！」
    2.27
    Activations Density 0.027%

    No Known Activations