© 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. 81508
    Prev
    Next
    INDEX
    Explanations

    Pacific geographical locations

    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
    
    -0.87
     why
    -0.82
    rendre
    -0.81
     Critic
    -0.81
    demics
    -0.79
     socc
    -0.79
    arrol
    -0.79
     aware
    -0.79
     akum
    -0.78
    Cree
    -0.77
    POSITIVE LOGITS
     Rim
    1.57
     Northwest
    1.25
     Coast
    1.25
     coast
    1.24
    Rim
    1.15
     rim
    1.15
     Palis
    1.14
     Ocean
    1.13
    coast
    1.10
    Coast
    1.09
    Activations Density 0.008%

    No Known Activations