© 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. 22-GEMMASCOPE-RES-131K
    7. 130104
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of health and safety protocols and procedures (e.g. curbside pickup, serving one person at a time, patrons encouraged to wear masks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    procedures will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     relationships
    -1.19
     want
    -1.17
    Enllaços
    -1.16
     or
    -1.02
     often
    -1.00
    Esperamos
    -1.00
     wants
    -1.00
    vajú
    -0.99
     Wikime
    -0.99
     could
    -0.97
    POSITIVE LOGITS
     everyone
    1.38
    ῳ
    1.23
     APPELLANT
    1.20
    给大家
    1.18
     everybody
    1.18
    全員
    1.17
     RESPONDENT
    1.17
     reż
    1.14
    ּוֹ
    1.13
     garantire
    1.13
    Activations Density 0.006%

    No Known Activations