© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49291
    Prev
    Next
    INDEX
    Explanations

    suburban and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     downtown
    -1.03
    taja
    -0.99
    bukkit
    -0.94
     rural
    -0.87
     Downtown
    -0.87
    Downtown
    -0.85
    Rural
    -0.80
     RURAL
    -0.79
    koh
    -0.76
    msen
    -0.76
    POSITIVE LOGITS
     suburban
    0.91
     Suburban
    0.90
     suburb
    0.89
     Concorde
    0.82
     IKEA
    0.81
     papillon
    0.78
    产生了
    0.76
     Hauts
    0.74
     Selangor
    0.74
    Geme
    0.73
    Activations Density 0.097%

    No Known Activations