© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    Southern + geographical descriptor

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

    the presence of the proper‐name token “Southern,” as in place or organization names.

    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
     canina
    -0.97
    🌰
    -0.87
     thắng
    -0.86
     красивая
    -0.85
    Ր
    -0.85
     alrededores
    -0.84
    endaten
    -0.84
     sockets
    -0.82
    Enigma
    -0.82
    ندی
    -0.81
    POSITIVE LOGITS
    most
    1.30
     California
    1.08
     Comfort
    1.02
     hemisphere
    1.00
     tier
    1.00
     Methodist
    0.91
     california
    0.88
     Gothic
    0.87
     comfort
    0.86
    California
    0.85
    Activations Density 0.022%

    No Known Activations