© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59805
    Prev
    Next
    INDEX
    Explanations

    exposure to or resistance to

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

    The neuron detects phrases containing "to" following words like "exposure," "resistance," or "access," typically in scientific or medical contexts.

    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
    )
    -2.59
    ";
    -1.80
    ).
    -1.79
     antemano
    -1.78
    ."
    -1.73
    );
    -1.71
    .",
    -1.68
    ;
    -1.60
    ",
    -1.60
     oder
    -1.59
    POSITIVE LOGITS
     from
    1.84
    </h6>
    1.79
    ÑOS
    1.63
     the
    1.59
    arashtra
    1.58
    where
    1.55
     having
    1.55
     становятся
    1.48
     where
    1.45
    总是
    1.45
    Activations Density 0.211%

    No Known Activations