© 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. 34-GEMMASCOPE-RES-131K
    7. 57241
    Prev
    Next
    INDEX
    Explanations

    stag, hen, bachelor parties

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

    The neuron strongly activates on occurrences of the word “stag” (e.g. “Stag Company,” “stag do,” etc.).

    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
    夫妻
    -0.91
    setViewportView
    -0.86
     Kisses
    -0.81
     Fleece
    -0.80
     匿名
    -0.75
     cudd
    -0.75
     produced
    -0.75
    کید
    -0.75
     tvrd
    -0.74
    ण
    -0.74
    POSITIVE LOGITS
     Maid
    1.08
     Bachelor
    1.06
     bachelor
    1.05
     bridesmaids
    1.04
    Maid
    1.00
     maid
    0.98
     penga
    0.97
     bache
    0.93
     hens
    0.93
     attendants
    0.89
    Activations Density 0.010%

    No Known Activations