© 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. 22-GEMMASCOPE-RES-131K
    7. 28072
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code snippets

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

    The neuron responds to numeric tokens (numbers, decimals, version‐style digit sequences, 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_22/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
    nú
    -0.81
    虧
    -0.81
     slightly
    -0.81
    하려
    -0.79
     it
    -0.79
     야
    -0.77
     usually
    -0.77
     into
    -0.75
    หร
    -0.75
     ligeramente
    -0.74
    POSITIVE LOGITS
    TagHelper
    0.92
    ᵗ
    0.87
     Mexique
    0.83
     reme
    0.82
     täv
    0.82
    水が
    0.80
     gitt
    0.80
     MCC
    0.79
    gingen
    0.78
    ᄏ
    0.78
    Activations Density 0.001%

    No Known Activations