© 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. 25554
    Prev
    Next
    INDEX
    Explanations

    $x_0$ or $x_n$ followed by zero or index

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

    The neuron fires on mathematical formula tokens—especially variable names with subscripts and standalone numeric symbols in equations.

    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
    Setelah
    -0.84
     cyclist
    -0.78
     Setelah
    -0.77
    Andrés
    -0.77
    pués
    -0.77
     جدید
    -0.76
     THIRD
    -0.76
    Yann
    -0.76
     terbaru
    -0.74
    Canceled
    -0.73
    POSITIVE LOGITS
    ₀
    1.09
     zero
    0.98
    ０
    0.98
    0
    0.95
    ૦
    0.95
     cero
    0.89
    初始
    0.88
     reference
    0.86
     obrigado
    0.85
     initial
    0.84
    Activations Density 0.020%

    No Known Activations