© 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. 22-GEMMASCOPE-RES-131K
    7. 9501
    Prev
    Next
    INDEX
    Explanations

    increasing complexity and demands

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

    The neuron primarily responds to comparative or quantitative “more/increasing” type terms—words that signal growth, rising demand, or higher degree (e.g. “more,” “increasing,” “growing,” “complexity”).

    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
     would
    -1.54
     could
    -1.20
    delion
    -1.14
    aría
    -1.10
    了一会儿
    -1.09
     pertenecen
    -1.03
     podría
    -1.02
     öppna
    -1.02
     tivesse
    -1.00
     BorderSide
    -0.99
    POSITIVE LOGITS
     increasingly
    1.85
     increasing
    1.78
     increased
    1.73
    increasing
    1.51
     demands
    1.50
    Increasing
    1.47
     Increasing
    1.38
    要求
    1.36
     Increased
    1.36
    越来越多
    1.34
    Activations Density 0.308%

    No Known Activations