© 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. 34-GEMMASCOPE-RES-131K
    7. 33689
    Prev
    Next
    INDEX
    Explanations

    facility and facilities

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

    The neuron consistently fires on the token “facility” (and its plural “facilities”), including in titles and headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     desenvolvimento
    -1.18
    啕
    -1.17
    妧
    -1.14
    新鮮
    -1.13
     propensity
    -1.11
     unforeseen
    -1.09
     probablement
    -1.05
     precisione
    -1.05
    嶮
    -1.03
     illuminating
    -1.02
    POSITIVE LOGITS
    設施
    1.48
    ’
    1.30
    设施
    1.20
    ”
    1.18
     constr
    1.13
    仑
    1.13
     xix
    1.10
    timis
    1.07
    чом
    1.06
    ueras
    1.05
    Activations Density 0.015%

    No Known Activations