© 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. 76580
    Prev
    Next
    INDEX
    Explanations

    arts, literature, and theatre geeks

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

    The neuron detects promotional or self-help marketing copy offering dating tips (e.g. “dating guide,” “tips for geeks and nerds,” “how to get her to like you being yourself,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    jaan
    -0.81
    aroos
    -0.80
    蹟
    -0.78
    跨
    -0.77
    传
    -0.77
    pretrained
    -0.76
    PLC
    -0.76
    改
    -0.75
    ismo
    -0.74
     chiến
    -0.74
    POSITIVE LOGITS
     nerd
    2.81
     nerds
    2.44
     ner
    2.44
     geek
    2.39
    nerd
    2.11
     Nerd
    2.03
    Nerd
    2.00
     Geek
    1.86
    geek
    1.85
    Geek
    1.62
    Activations Density 0.052%

    No Known Activations