© 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. 59065
    Prev
    Next
    INDEX
    Explanations

    the name Dick

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

    The neuron strongly activates on occurrences of the proper name “Dick.”

    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
     were
    -2.84
     painstaking
    -2.61
     reminiscent
    -2.58
     enchanting
    -2.53
    婠
    -2.48
    ༷
    -2.47
     resounding
    -2.45
    昞
    -2.44
    ⸂
    -2.39
    囿
    -2.38
    POSITIVE LOGITS
    鋨
    2.69
    ساعت
    2.25
    ,
    2.25
     贺
    2.22
     brill
    2.22
    汌
    2.20
     και
    2.20
     risiko
    2.14
    "",
    2.14
    ření
    2.13
    Activations Density 0.003%

    No Known Activations