© 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. 45210
    Prev
    Next
    INDEX
    Explanations

    pathogen and infection

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

    This neuron detects words related to disease-causing organisms, particularly the word "pathogen".

    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
    </h3>
    -3.81
    榈
    -3.23
    櫚
    -2.56
    。"
    -2.48
    .".
    -2.44
    }$.
    -2.41
    」（
    -2.39
    rierte
    -2.34
    ?"
    -2.33
    .”
    -2.30
    POSITIVE LOGITS
    </b>
    3.47
    ↵
    3.22
    {
    2.56
    '
    2.30
    n
    2.30
     reciente
    2.25
     you
    2.22
    </td>
    2.22
    を作って
    2.22
    一些
    2.17
    Activations Density 0.018%

    No Known Activations