© 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. 77023
    Prev
    Next
    INDEX
    Explanations

    island places and associated information

    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
    cities
    -1.02
     cities
    -0.94
    Cities
    -0.90
     Cities
    -0.90
     railroads
    -0.90
     recens
    -0.87
     hiệp
    -0.86
    愀
    -0.82
    CONFLICT
    -0.81
     Всё
    -0.81
    POSITIVE LOGITS
     island
    1.43
    island
    1.40
    Island
    1.38
     Island
    1.36
    Bermuda
    1.25
     islanders
    1.23
     Bermuda
    1.23
     Government
    1.22
     Cayman
    1.20
     депута
    1.16
    Activations Density 0.007%

    No Known Activations