© 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. 68393
    Prev
    Next
    INDEX
    Explanations

    of occurrence

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

    The neuron reliably activates on the preposition “of.”

    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
    <bos>
    -2.88
    the
    -2.80
    這些
    -2.59
    噌
    -2.41
    這種
    -2.33
    鼋
    -2.28
     эту
    -2.22
     regards
    -2.20
    คุณ
    -2.17
     اين
    -2.14
    POSITIVE LOGITS
    r
    3.31
    ’
    2.73
     course
    2.55
     sorts
    2.44
    ak
    2.34
    s
    2.30
    ter
    2.27
    “
    2.25
     inga
    2.25
     They
    2.25
    Activations Density 0.053%

    No Known Activations