© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73629
    Prev
    Next
    INDEX
    Explanations

    unilateral medical conditions

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

    The neuron detects the word "unilateral" and personal names containing "Felipe".

    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
    $
    -3.56
    '
    -3.17
    ’
    -3.03
    “
    -2.98
     In
    -2.77
    }
    -2.64
    l
    -2.63
    了一
    -2.39
    section
    -2.33
     That
    -2.28
    POSITIVE LOGITS
    鴴
    2.94
    盉
    2.84
     trám
    2.80
    鹛
    2.77
    
    2.77
    瘊
    2.69
     któ
    2.64
    衚
    2.61
    铼
    2.61
     odkazy
    2.58
    Activations Density 0.010%

    No Known Activations