© 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. 34920
    Prev
    Next
    INDEX
    Explanations

    setting alarms

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

    The neuron strongly activates on mentions of an “Alarm Clock” product name (e.g. “Solid Alarm Clock Extended,” “Wake up with…,” etc.), effectively identifying references to that alarm-clock app or device.

    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
    INSTALLATION
    -0.80
     Neurol
    -0.79
    größe
    -0.78
     câu
    -0.77
     الاعت
    -0.75
     anthropology
    -0.75
     dehydrogenase
    -0.73
     coefficient
    -0.72
    letka
    -0.71
     بالن
    -0.71
    POSITIVE LOGITS
     clock
    1.38
     alarm
    1.30
     radio
    1.28
     Alarm
    1.28
    alarm
    1.15
     wake
    1.14
     docking
    1.11
     Radio
    1.08
     Wake
    1.04
     радио
    1.04
    Activations Density 0.013%

    No Known Activations