© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47968
    Prev
    Next
    INDEX
    Explanations

    San Francisco landmarks and institutions

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

    The neuron detects named entities—proper names of people, places, and organizations.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Chak
    -0.82
    ιού
    -0.79
     PPI
    -0.79
     Riverside
    -0.78
    晓
    -0.78
     følge
    -0.77
     PV
    -0.75
    ﹔
    -0.74
     imidlertid
    -0.73
     Southwestern
    -0.72
    POSITIVE LOGITS
     SF
    2.13
    SF
    2.05
    Oakland
    1.93
     Oakland
    1.88
     San
    1.81
    Stanford
    1.68
     Stanford
    1.62
     BART
    1.54
    Berkeley
    1.51
    sf
    1.48
    Activations Density 0.158%

    No Known Activations