© 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. 10-GEMMASCOPE-RES-131K
    7. 41032
    Prev
    Next
    INDEX
    Explanations

    pierce and piercing actions or names

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

    This neuron activates on occurrences of the substring “pierce,” especially the proper name “Pierce.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     encompassing
    -3.05
     Would
    -2.88
    ઁ
    -2.78
     Currently
    -2.67
     Definitely
    -2.63
     pervasive
    -2.63
     Usually
    -2.61
     when
    -2.56
     undeniably
    -2.56
     While
    -2.53
    POSITIVE LOGITS
    潆
    3.06
     betreffende
    2.89
    archiwizowane
    2.89
    3
    2.78
    臜
    2.77
     zubehör
    2.75
     lauded
    2.70
    獴
    2.70
    镚
    2.69
    轳
    2.69
    Activations Density 0.006%

    No Known Activations