© 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. 13614
    Prev
    Next
    INDEX
    Explanations

    been + verb-ing

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

    The neuron specifically detects occurrences of the word “been.”

    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
     that
    -1.95
     still
    -1.87
     first
    -1.84
     when
    -1.77
     one
    -1.73
     not
    -1.63
     what
    -1.45
     currently
    -1.45
     slightly
    -1.42
     fourth
    -1.41
    POSITIVE LOGITS
    since
    1.74
     منذ
    1.71
     since
    1.58
    Seit
    1.41
    ############
    1.37
     been
    1.35
    Been
    1.34
    recently
    1.32
    ###########
    1.31
    <mask>
    1.30
    Activations Density 0.056%

    No Known Activations