© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31616
    Prev
    Next
    INDEX
    Explanations

    Chengdu Sichuan province

    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
     Peterborough
    -0.93
     Delaware
    -0.85
    Delaware
    -0.85
     Collingwood
    -0.85
     Brunswick
    -0.81
    bles
    -0.78
     excav
    -0.74
    vetor
    -0.74
     Kø
    -0.73
    viato
    -0.73
    POSITIVE LOGITS
     Chengdu
    1.63
     Sichuan
    1.44
    Alberta
    1.08
    成都
    1.02
     Arkansas
    0.98
    Arkansas
    0.98
     Alberta
    0.96
    四川
    0.94
     Panda
    0.89
     Baylor
    0.88
    Activations Density 0.019%

    No Known Activations