© 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. 1427
    Prev
    Next
    INDEX
    Explanations

    words ending in ings

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

    This neuron detects the suffix “ings” at the ends of words.

    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
    If
    -3.08
    \
    -3.08
    There
    -2.97
    Having
    -2.95
    Just
    -2.92
    When
    -2.88
    Let
    -2.80
     یا
    -2.78
    Even
    -2.75
     atau
    -2.73
    POSITIVE LOGITS
     evocative
    3.06
     dilapidated
    2.81
     relativamente
    2.77
     sumptuous
    2.73
    翕
    2.66
     creando
    2.58
    ญี่ป
    2.56
    
    2.55
     causando
    2.55
     procurando
    2.55
    Activations Density 0.025%

    No Known Activations