© 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. 10-GEMMASCOPE-RES-131K
    7. 42630
    Prev
    Next
    INDEX
    Explanations

    process of followed by action

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

    The neuron selectively activates on the word “process,” flagging occurrences of that term in procedural or methodological descriptions.

    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
    {
    -2.05
    合适的
    -2.00
    ご予約
    -2.00
     mundos
    -1.93
     estrela
    -1.91
    皤
    -1.90
    ;\\
    -1.88
    長い
    -1.86
     famous
    -1.86
     kijk
    -1.82
    POSITIVE LOGITS
    ”
    2.88
    v
    2.27
    y
    1.98
    if
    1.96
    z
    1.91
    StreetMap
    1.90
    ta
    1.85
    u
    1.84
    ak
    1.84
    me
    1.80
    Activations Density 0.027%

    No Known Activations