© 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. 22-GEMMASCOPE-RES-131K
    7. 32865
    Prev
    Next
    INDEX
    Explanations

    locations and rooms

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

    The neuron fires on nouns naming specific amenities, attractions, or facility features (e.g. restaurant, food court, spa, arcade, barn, lobby) when they appear in a description.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     from
    -1.97
     or
    -1.83
     in
    -1.70
     because
    -1.59
     by
    -1.56
     through
    -1.47
     on
    -1.46
     (
    -1.38
     as
    -1.35
     may
    -1.33
    POSITIVE LOGITS
     noter
    1.59
     plafon
    1.59
     voer
    1.59
     kristal
    1.52
     interieur
    1.51
     logis
    1.49
     departement
    1.48
     sains
    1.47
     fondamental
    1.46
     stadion
    1.45
    Activations Density 0.048%

    No Known Activations