© 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. 22-GEMMASCOPE-RES-131K
    4. 73999
    Prev
    Next
    INDEX
    Explanations

    critical thinking

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

    This neuron responds to occurrences of the word “critical.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    逦
    -2.66
     Either
    -2.55
     weiteren
    -2.36
    越是
    -2.36
     Acknowled
    -2.34
     Applying
    -2.28
     Existe
    -2.27
     Ensuring
    -2.25
     Their
    -2.23
    粍
    -2.22
    POSITIVE LOGITS
    鋮
    2.88
    that
    2.75
    i
    2.63
     penghar
    2.52
     techniczne
    2.48
    渽
    2.47
     bahwa
    2.45
    鄚
    2.33
     nocy
    2.31
    瑧
    2.23
    Activations Density 0.021%

    No Known Activations