© 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. 90281
    Prev
    Next
    INDEX
    Explanations

    controlling for

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

    The neuron fires on statistical qualifier phrases—e.g. “controlling for,” “other factors being equal,” “all else being equal.”

    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
     });
    -1.36
     departe
    -1.36
     rute
    -1.28
     feb
    -1.27
     sosi
    -1.26
     asma
    -1.24
    鹛
    -1.21
     camiset
    -1.20
     are
    -1.19
     dito
    -1.19
    POSITIVE LOGITS
    You
    1.55
    It
    1.53
     graciosas
    1.52
    _
    1.48
    Your
    1.41
    Also
    1.40
     agradable
    1.40
    At
    1.37
     positivas
    1.35
    صدق
    1.34
    Activations Density 0.011%

    No Known Activations