© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70836
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb or article

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

    The neuron selectively activates on occurrences of the word “to,” whether as a preposition or an infinitive marker.

    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
    </strong>
    -1.64
    歘
    -1.59
    actéristi
    -1.58
    蓠
    -1.56
     élevées
    -1.55
     ")[
    -1.52
    ——”
    -1.52
    uran
    -1.50
     diferente
    -1.48
     différents
    -1.48
    POSITIVE LOGITS
     there
    2.23
     by
    1.94
    ."
    1.85
    there
    1.62
     a
    1.57
     is
    1.56
     only
    1.55
    ウィキ
    1.48
     with
    1.45
     '
    1.44
    Activations Density 0.066%

    No Known Activations