© 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. 103956
    Prev
    Next
    INDEX
    Explanations

    reporter, reporter gene

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

    The neuron identifies job titles related to reporting news or information, particularly focusing on the word "reporter".

    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
    ↵↵
    -3.44
     edgy
    -3.00
     affectionate
    -2.81
     neuen
    -2.80
     oppressive
    -2.67
     eerie
    -2.66
     crafty
    -2.61
     defiant
    -2.61
     agility
    -2.55
     extravagant
    -2.48
    POSITIVE LOGITS
    鬭
    3.00
    諏
    2.91
     resides
    2.83
     leeftijd
    2.73
     funt
    2.67
    鷥
    2.61
     verschillen
    2.56
    棡
    2.56
    縂
    2.55
    蚡
    2.53
    Activations Density 0.004%

    No Known Activations