© 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. 34-GEMMASCOPE-RES-131K
    7. 99834
    Prev
    Next
    INDEX
    Explanations

    brown university and common collocations

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

    The neuron consistently activates on the substring “Brown” (i.e. occurrences of the word “Brown,” whether as a name or color).

    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
     whitish
    -0.88
     Там
    -0.82
    党员
    -0.81
    剣
    -0.78
     abbre
    -0.77
    GX
    -0.77
    違う
    -0.77
    atkan
    -0.76
    在于
    -0.75
    在你
    -0.74
    POSITIVE LOGITS
    lee
    1.16
     Brown
    1.13
     brune
    0.94
    Brown
    0.93
    stone
    0.88
    stones
    0.88
    brown
    0.86
     marmor
    0.85
     haired
    0.85
    づらい
    0.85
    Activations Density 0.015%

    No Known Activations