© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7177
    Prev
    Next
    INDEX
    Explanations

    speaks to

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

    This neuron detects instances of the word “to” when it’s part of a “verb to (object)” construction (e.g. “speaks to,” “speak to,” “speaking truth to power”).

    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
    9
    -1.63
    ”
    -1.57
    かた
    -1.53
     keinem
    -1.50
    3
    -1.49
    7
    -1.47
     الأخرى
    -1.45
    -1.45
     akzeptieren
    -1.41
    ekan
    -1.40
    POSITIVE LOGITS
    sterious
    1.86
     you
    1.77
    ܖ
    1.70
    ㈯
    1.69
     kinderen
    1.66
     captivated
    1.64
     fortun
    1.63
    〼
    1.61
    desire
    1.58
    ޏ
    1.56
    Activations Density 0.015%

    No Known Activations