© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84202
    Prev
    Next
    INDEX
    Explanations

    man or woman of

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

    This neuron detects the phrase “man of” (e.g. “a man of stocky build,” “a man of deep faith,” “a man of the Enlightenment”).

    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
    \
    -2.30
    步驟
    -1.79
    鱘
    -1.78
     zapato
    -1.75
     étrang
    -1.75
     harika
    -1.72
    两者
    -1.66
     pinjaman
    -1.66
     celu
    -1.64
    लिए
    -1.64
    POSITIVE LOGITS
    2
    2.16
    However
    1.76
     kemudian
    1.74
    哎呀
    1.74
     If
    1.71
    ?)
    1.70
    jęcie
    1.68
     With
    1.68
    /
    1.65
     також
    1.59
    Activations Density 0.016%

    No Known Activations