© 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. 130877
    Prev
    Next
    INDEX
    Explanations

    bringing to

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

    The neuron selectively activates on the word “to.”

    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
    \
    -2.67
     \
    -2.39
     $
    -2.30
    橚
    -2.08
     \\
    -1.84
    ра
    -1.84
    item
    -1.82
    ik
    -1.77
    \_
    -1.76
    𓐍
    -1.76
    POSITIVE LOGITS
     工場
    2.16
    砹
    2.05
    .’
    1.95
     unterschied
    1.87
    brtc
    1.80
     案内
    1.77
     opportune
    1.77
    </h4>
    1.77
     jewish
    1.74
    此外
    1.73
    Activations Density 0.013%

    No Known Activations