© 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. 11421
    Prev
    Next
    INDEX
    Explanations

    increasing or decreasing quantities

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

    This neuron detects words ending in “-ing,” i.e. present-participle or gerund verb forms.

    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
     avancer
    -1.73
     animali
    -1.72
     zoude
    -1.70
     vanille
    -1.63
     cette
    -1.62
    =“
    -1.60
    "-"
    -1.58
    ributes
    -1.57
    ftar
    -1.56
    countries
    -1.55
    POSITIVE LOGITS
     We
    2.06
     our
    1.86
     vehemently
    1.79
     With
    1.70
     relentlessly
    1.63
     have
    1.59
     slowly
    1.58
     prevalent
    1.55
     before
    1.54
     changing
    1.51
    Activations Density 0.093%

    No Known Activations