© 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. 22-GEMMASCOPE-RES-131K
    7. 130650
    Prev
    Next
    INDEX
    Explanations

    This neuron detects administrative and logistical text, especially registration details for events.

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

    event participation and registration

    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
     always
    -1.13
     sometimes
    -1.13
     whenever
    -1.06
    \
    -1.05
    日常
    -1.05
     new
    -1.03
    mú
    -1.01
     usually
    -1.00
    回到
    -1.00
     NEVER
    -1.00
    POSITIVE LOGITS
     participants
    1.44
     confirme
    1.34
     participante
    1.22
    istungen
    1.21
     participant
    1.20
     participation
    1.18
    申し込み
    1.16
    早めに
    1.13
     wcześniej
    1.13
     registration
    1.12
    Activations Density 0.030%

    No Known Activations