© 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. 60506
    Prev
    Next
    INDEX
    Explanations

    spatial alignment and opposition

    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
     შ
    -0.91
    vänd
    -0.85
    หวัด
    -0.84
     múltiples
    -0.83
     trabal
    -0.82
     DIRECTION
    -0.81
    瀛
    -0.81
     camisetas
    -0.80
     galinha
    -0.80
    附近
    -0.78
    POSITIVE LOGITS
     directly
    3.39
    directly
    2.59
     Directly
    2.53
     directamente
    2.31
     exactly
    2.28
     directement
    2.22
     diretamente
    2.19
     direttamente
    2.06
     прямо
    1.97
     přímo
    1.90
    Activations Density 0.076%

    No Known Activations