© 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. 65221
    Prev
    Next
    INDEX
    Explanations

    android xml namespaces

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

    The neuron strongly activates on numeric literal tokens (integer values) wherever they appear.

    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
     Grows
    -0.73
     Prophe
    -0.71
    Monty
    -0.70
     Montessori
    -0.70
     Jans
    -0.69
     Monty
    -0.68
     MATRIX
    -0.67
     ralph
    -0.67
    без
    -0.66
    Geri
    -0.66
    POSITIVE LOGITS
    ู้
    0.79
    Tag
    0.77
    tags
    0.76
    Tags
    0.76
     Tag
    0.75
     Simmons
    0.73
     integers
    0.73
     Unit
    0.73
     tags
    0.71
    喻
    0.71
    Activations Density 0.063%

    No Known Activations