© 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. 10-GEMMASCOPE-RES-131K
    7. 795
    Prev
    Next
    INDEX
    Explanations

    carriage and cartilage

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects references to carriages and similar vehicles or transportation compartments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    埽
    -3.48
    硨
    -3.45
     広場
    -2.81
    $
    -2.80
     撮っ
    -2.70
    銲
    -2.69
    謦
    -2.64
    
    -2.64
    拶
    -2.58
    ⚢
    -2.56
    POSITIVE LOGITS
    section
    3.19
    e
    3.19
     They
    3.08
     When
    3.05
     After
    3.05
     During
    2.73
     clín
    2.72
    enfone
    2.52
     Когда
    2.52
     danach
    2.50
    Activations Density 0.004%

    No Known Activations