© 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. 101967
    Prev
    Next
    INDEX
    Explanations

    for ... that

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

    The neuron fires on occurrences of the preposition “for.”

    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
     a
    -1.95
    \
    -1.90
     all
    -1.41
     an
    -1.32
    有些
    -1.30
        
    -1.28
     still
    -1.26
    诸多
    -1.26
     "
    -1.23
     our
    -1.23
    POSITIVE LOGITS
     possib
    1.53
    ügel
    1.52
     człowieka
    1.52
     новых
    1.52
    seitig
    1.38
     keď
    1.38
     dzisiaj
    1.38
     obtenidos
    1.36
     było
    1.35
     clínicas
    1.35
    Activations Density 0.118%

    No Known Activations