© 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. 64496
    Prev
    Next
    INDEX
    Explanations

    residential areas

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

    The neuron fires strongly on unusually long tokens (i.e. multi‐character words), essentially detecting “long words.”

    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
    L
    -1.13
     and
    -1.10
     needed
    -1.07
     entrambi
    -1.02
     xícara
    -1.01
    everything
    -0.94
     TRABAJO
    -0.94
     anything
    -0.94
    城区
    -0.92
     everything
    -0.91
    POSITIVE LOGITS
     perumahan
    1.26
     where
    1.16
     sini
    1.15
     köy
    1.15
     community
    1.12
     village
    1.11
     amenities
    1.11
     minne
    1.10
     complexes
    1.08
     konsep
    1.07
    Activations Density 0.037%

    No Known Activations