© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70890
    Prev
    Next
    INDEX
    Explanations

    sensors and detection components

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

    The neuron activates on mentions of sensing or detection devices (e.g. “sensor,” “motion detector,” “heat sensor,” “window sensor,” etc.).

    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
    噚
    -1.43
    !!</
    -1.40
     only
    -1.38
    鲻
    -1.38
    лася
    -1.38
     EARTH
    -1.36
     Chá
    -1.33
    ujuk
    -1.32
    але
    -1.32
     lahir
    -1.32
    POSITIVE LOGITS
     decides
    1.59
    that
    1.48
     ваш
    1.48
     he
    1.44
    帮你
    1.41
     /
    1.40
    再加上
    1.38
    看你
    1.38
    みます
    1.37
    你想
    1.35
    Activations Density 0.045%

    No Known Activations