© 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. 104239
    Prev
    Next
    INDEX
    Explanations

    inoculated into something

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

    The neuron detects the word "inoculated" and related terms in scientific contexts about introducing microorganisms or substances into test subjects.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron picks out quantitative experimental measurements, especially inoculation counts and related numeric data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    H
    -2.73
    B
    -2.56
    S
    -2.44
    ：「
    -2.34
    W
    -2.31
    Of
    -2.25
    si
    -2.23
    C
    -2.20
    Y
    -2.19
    st
    -2.17
    POSITIVE LOGITS
     undertaken
    2.17
     conceived
    2.14
    㩒
    2.03
     awarded
    2.03
    も同じ
    2.02
    枓
    2.02
    䊐
    2.00
    踅
    1.99
     firmado
    1.95
    鈰
    1.92
    Activations Density 0.005%

    No Known Activations