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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73447
    Prev
    Next
    INDEX
    Explanations

    Bay Area locations and legal districts

    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
     obserw
    -0.91
     NX
    -0.76
    <0x92>
    -0.74
     observations
    -0.71
    젯
    -0.70
     inputs
    -0.68
    ommer
    -0.68
    왕
    -0.67
     обслуживания
    -0.67
    Input
    -0.67
    POSITIVE LOGITS
    Oakland
    1.17
     Bay
    1.16
     Oakland
    1.12
     San
    1.11
     bay
    1.05
    BAY
    0.91
     BART
    0.91
    San
    0.90
    BART
    0.88
    bay
    0.87
    Activations Density 0.041%

    No Known Activations