© 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. 58549
    Prev
    Next
    INDEX
    Explanations

    courtship rituals and outreach

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

    The neuron detects terms related to outreach and community engagement programs.

    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
     what
    -2.34
     one
    -2.20
    of
    -2.06
     concentrado
    -1.97
     вашего
    -1.96
    苹
    -1.94
    此处
    -1.92
    ischof
    -1.91
    ｵ
    -1.90
     give
    -1.84
    POSITIVE LOGITS
    “
    2.73
     για
    2.70
    
    2.61
    nad
    2.44
     citoy
    2.36
    踅
    2.34
    ௅
    2.33
    
    2.31
    s
    2.30
    
    2.30
    Activations Density 0.001%

    No Known Activations