© 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. 112861
    Prev
    Next
    INDEX
    Explanations

    to + verb or noun

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

    The neuron strongly responds to the preposition “to” (and occasionally related directional prepositions like “from”), marking infinitive or relational phrases.

    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
     \
    -2.33
    \
    -2.30
     $
    -1.98
     you
    -1.92
     For
    -1.91
     September
    -1.83
     July
    -1.82
     Thirty
    -1.77
    .
    -1.71
     June
    -1.70
    POSITIVE LOGITS
    我们
    1.95
     ingredi
    1.70
    ㌧
    1.70
     mantan
    1.70
    lidad
    1.70
     チキン
    1.68
    鑪
    1.68
    in
    1.66
     wagen
    1.61
    ﹕
    1.61
    Activations Density 0.036%

    No Known Activations