© 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. 22-GEMMASCOPE-RES-131K
    7. 84378
    Prev
    Next
    INDEX
    Explanations

    actions and analyses

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

    This neuron detects gerund‐form verbs (the “-ing” words) used as titles or section headings.

    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
    
    -1.86
    见的
    -1.83
     pengar
    -1.73
    们的
    -1.66
     corriger
    -1.63
     poë
    -1.63
     åren
    -1.61
     dekoratif
    -1.60
     الاد
    -1.60
     árboles
    -1.59
    POSITIVE LOGITS
     the
    2.84
     through
    2.41
     from
    2.33
     our
    2.33
     your
    2.22
     as
    2.08
     While
    2.00
     for
    1.91
     Not
    1.91
     so
    1.90
    Activations Density 0.084%

    No Known Activations