© 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. 70828
    Prev
    Next
    INDEX
    Explanations

    on/off, open/closed, stop/start

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

    The neuron fires on words that indicate toggling a state—especially “off” and “on” (and related disable/enable or start/stop) markers.

    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
    -1.49
     "
    -1.48
    氏が
    -1.43
     serait
    -1.34
     quienes
    -1.34
     から
    -1.32
     Who
    -1.30
     
    -1.28
     quien
    -1.28
     で
    -1.28
    POSITIVE LOGITS
     with
    1.50
     of
    1.46
     torino
    1.44
     kuhusu
    1.41
    different
    1.35
     through
    1.34
     using
    1.34
    ementara
    1.33
     березня
    1.33
     різних
    1.29
    Activations Density 0.070%

    No Known Activations