© 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. 11772
    Prev
    Next
    INDEX
    Explanations

    ter with chemical suffixes

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

    The neuron detects the prefix "ter" in scientific and medical terminology like "teratoma," "teratogenic," "terpolymer," and dialectical speech like "ter" for "to."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates on occurrences of the character sequence “ter” within 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
    鲧
    -3.61
     gustaMe
    -3.44
    othes
    -3.16
    搋
    -3.02
    珰
    -3.02
     fêtes
    -2.98
    猹
    -2.97
     débris
    -2.95
    ᆞ
    -2.94
    嫘
    -2.94
    POSITIVE LOGITS
    =
    3.98
    [
    3.88
    ()
    3.41
    {
    3.41
     '
    3.38
    3
    3.34
    &
    3.31
     When
    3.19
     einige
    3.16
    _
    3.16
    Activations Density 0.009%

    No Known Activations