© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103048
    Prev
    Next
    INDEX
    Explanations

    common cold and respiratory infections

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

    words and phrases related to respiratory illnesses, especially "cold" and associated symptoms.

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

    The neuron specifically fires on mentions of “cold” in the sense of the common cold or related cold-like respiratory illness.

    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
     of
    -2.05
     to
    -1.47
    ib
    -1.28
    ite
    -1.27
    —
    -1.18
    on
    -1.17
     t
    -1.16
     at
    -1.15
    了不少
    -1.15
    一趟
    -1.14
    POSITIVE LOGITS
     aukš
    1.48
    ających
    1.46
     daugiau
    1.46
    蝨
    1.45
     nový
    1.40
     Atención
    1.39
    engertian
    1.39
    大军
    1.38
     gydy
    1.35
     bemerkt
    1.34
    Activations Density 0.045%

    No Known Activations