© 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. 70854
    Prev
    Next
    INDEX
    Explanations

    part of

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

    The neuron strongly activates on the word “of” when it appears as part of the phrase “part 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_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
    .
    -3.95
    )
    -2.38
    0
    -2.17
    '
    -2.16
    wakili
    -2.06
     一
    -1.99
     is
    -1.98
    々
    -1.93
    </h3>
    -1.92
    ""
    -1.88
    POSITIVE LOGITS
    荦
    2.27
    viembre
    2.23
    </b>
    2.14
    澂
    2.02
    新能源
    2.02
     whom
    2.00
     incapa
    1.95
    蠃
    1.93
     our
    1.91
    ꦫ
    1.91
    Activations Density 0.025%

    No Known Activations