© 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. 34524
    Prev
    Next
    INDEX
    Explanations

    distant and far away

    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
     spirito
    -0.92
    thiet
    -0.88
     portable
    -0.85
     tomadas
    -0.83
    🏻‍♀️
    -0.82
     osta
    -0.82
     ricor
    -0.82
     spis
    -0.82
    ίζει
    -0.78
    מעות
    -0.78
    POSITIVE LOGITS
    away
    1.42
     distant
    1.41
     away
    1.30
    distance
    1.28
     distances
    1.22
     distance
    1.21
     Distant
    1.16
     geographically
    1.04
     remote
    1.01
     REMOTE
    1.00
    Activations Density 0.021%

    No Known Activations