© 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. 42526
    Prev
    Next
    INDEX
    Explanations

    time expressions and adverbs

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

    The neuron is a specialist for adverbial modifiers—especially temporal expressions (e.g. “last week,” “last night,” “this afternoon”) and manner/dose-dependency adverbs (e.g. “quickly,” “comprehensively,” “dependently”).

    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
     that
    -1.88
     a
    -1.68
     on
    -1.58
     even
    -1.52
     it
    -1.48
     indivíduo
    -1.31
     cuillère
    -1.30
     in
    -1.27
    ˋ
    -1.26
    мл
    -1.23
    POSITIVE LOGITS
    ly
    1.85
     attraverso
    1.65
     інші
    1.52
    our
    1.41
    stris
    1.41
    幾天
    1.38
     світу
    1.34
     outros
    1.34
     estrenar
    1.34
    不一樣
    1.33
    Activations Density 0.201%

    No Known Activations