© 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. 130770
    Prev
    Next
    INDEX
    Explanations

    most and best

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

    The neuron activates on the word “most,” especially when used to mark a superlative emphasis (e.g. “love most,” “matters most,” “remember most”).

    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
     Through
    -1.41
     (−
    -1.38
    んびり
    -1.38
     Wartawan
    -1.38
    ࿚
    -1.36
     you
    -1.34
    真正的
    -1.32
    Their
    -1.32
    Now
    -1.31
    нали
    -1.30
    POSITIVE LOGITS
    饪
    1.88
     than
    1.81
    騖
    1.75
     about
    1.70
     then
    1.63
     on
    1.58
     his
    1.55
     these
    1.52
     wody
    1.52
     jPanel
    1.46
    Activations Density 0.006%

    No Known Activations