© 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. 78399
    Prev
    Next
    INDEX
    Explanations

    Are

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

    The neuron strongly activates on the token “are” (in any casing or as part of names/subwords).

    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
    軼
    -0.80
    株式
    -0.79
    姿勢
    -0.77
     it
    -0.76
    人と
    -0.75
    łgor
    -0.74
    ese
    -0.74
    轟
    -0.73
    選択肢
    -0.72
    helin
    -0.71
    POSITIVE LOGITS
     you
    1.01
     Aer
    0.98
     Aren
    0.90
     there
    0.88
     Zweig
    0.86
     Arre
    0.84
     RUE
    0.82
    Aer
    0.82
     They
    0.80
    σκε
    0.80
    Activations Density 0.014%

    No Known Activations