© 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. 87189
    Prev
    Next
    INDEX
    Explanations

    Zak names and benzoate

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

    This neuron detects people's names, particularly first names like "Zak" and chemical terms like "benzo" compounds.

    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
     ſever
    -3.48
    齶
    -3.19
     Inſ
    -2.89
    翃
    -2.84
    
    -2.78
     But
    -2.78
    ﺀ
    -2.69
    釤
    -2.64
     ſou
    -2.63
    傒
    -2.63
    POSITIVE LOGITS
    F
    3.31
    ]
    3.22
    {
    3.20
    4
    2.95
    1
    2.92
    \
    2.84
    -
    2.84
    All
    2.75
    ↵↵
    2.72
    C
    2.64
    Activations Density 0.007%

    No Known Activations