© 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. 98330
    Prev
    Next
    INDEX
    Explanations

    XML tags and specific keys

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

    The neuron selectively activates on numeric tokens (numbers and digit sequences) in the text.

    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
    Minecraft
    -0.81
     لی
    -0.79
    websites
    -0.77
    mockMvc
    -0.76
    볍
    -0.75
    checkOut
    -0.74
    (">
    -0.73
     porous
    -0.73
     pandangan
    -0.72
     mü
    -0.71
    POSITIVE LOGITS
     tasks
    1.08
     Decorations
    0.91
     buildings
    0.85
    araoh
    0.82
     neighbor
    0.81
     年级
    0.81
    Upgradeable
    0.80
     energy
    0.79
     Tasks
    0.79
    Tasks
    0.79
    Activations Density 0.013%

    No Known Activations