© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91501
    Prev
    Next
    INDEX
    Explanations

    hacks, tips, and tricks

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

    The neuron detects clickbait–style promotional headline phrasing, especially the “this one weird trick” pattern.

    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
    ovatel
    -0.79
    一邊
    -0.78
    笈
    -0.75
    nehå
    -0.73
    ởi
    -0.71
    pointment
    -0.71
     必要
    -0.71
    StringBuilder
    -0.71
    pointments
    -0.70
    毀
    -0.70
    POSITIVE LOGITS
     tricks
    5.13
     trick
    4.94
    trick
    3.78
    tricks
    3.77
     Tricks
    3.47
     Trick
    3.39
     technique
    3.22
     techniques
    3.13
    Trick
    3.11
     truco
    2.78
    Activations Density 0.138%

    No Known Activations