© 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. 34-GEMMASCOPE-RES-131K
    7. 79555
    Prev
    Next
    INDEX
    Explanations

    Louisiana place names

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

    The neuron strongly fires on sequences of capitalized words forming multi‐word proper names or official titles (e.g. place names, agencies, parks).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Dob
    -0.72
     Shreveport
    -0.72
     па
    -0.71
     సం
    -0.71
     bouch
    -0.70
     porter
    -0.69
     Hit
    -0.68
     Dob
    -0.68
     voy
    -0.68
    валь
    -0.66
    POSITIVE LOGITS
    じゅ
    0.97
     UCLA
    0.81
    agna
    0.81
     Rens
    0.79
    oidal
    0.77
     Verkaufs
    0.77
     สวย
    0.76
     sealant
    0.76
     يول
    0.74
     gamis
    0.73
    Activations Density 0.021%

    No Known Activations