© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 86748
    Prev
    Next
    INDEX
    Explanations

    Victoria's Secret

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

    The neuron is highly specialized to fire on the character sequence “Swane,” as in the name Swanepoel.

    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
     all
    -1.02
     Tüm
    -0.98
     during
    -0.96
     any
    -0.96
     within
    -0.94
     commonly
    -0.94
     where
    -0.94
     seemingly
    -0.90
     in
    -0.90
     on
    -0.90
    POSITIVE LOGITS
    嫉妒
    0.97
     звука
    0.96
    a
    0.94
     Aa
    0.90
    可以看到
    0.88
     feront
    0.87
    ❿
    0.86
     évidemment
    0.86
     财
    0.85
     directement
    0.85
    Activations Density 0.000%

    No Known Activations