© 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. 67690
    Prev
    Next
    INDEX
    Explanations

    even followed by verb

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

    This neuron detects occurrences of the adverb “even” (especially in intensifying phrases like “didn’t even,” “haven’t even,” etc.).

    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
     and
    -1.52
     alſo
    -1.48
     également
    -1.36
     επίσης
    -1.31
    
    -1.29
     neither
    -1.27
     nevertheless
    -1.27
    だけではなく
    -1.27
     ALSO
    -1.25
     Però
    -1.25
    POSITIVE LOGITS
     even
    1.91
     даже
    1.91
     навіть
    1.72
     siquiera
    1.63
     Even
    1.60
    Even
    1.51
     nawet
    1.45
     حتی
    1.34
     zelfs
    1.29
     Даже
    1.27
    Activations Density 0.022%

    No Known Activations