© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15756
    Prev
    Next
    INDEX
    Explanations

    in [location/time]

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

    The neuron fires on occurrences of the preposition “in,” especially when it introduces a location or setting.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </b>
    -1.86
    睒
    -1.52
     verkau
    -1.50
    理由は
    -1.45
     transacciones
    -1.43
     garantías
    -1.41
     também
    -1.38
    lgari
    -1.37
     drücken
    -1.36
     letz
    -1.34
    POSITIVE LOGITS
     of
    1.80
     Prancis
    1.62
     Père
    1.52
    TING
    1.49
    🤡
    1.48
    🐾
    1.45
     Pemer
    1.41
    🤠
    1.35
     Instead
    1.34
     ensuite
    1.34
    Activations Density 0.013%

    No Known Activations