© 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. 49013
    Prev
    Next
    INDEX
    Explanations

    shortest path with negative edges

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

    The neuron is triggered by numeric literals (sequences of digits) in code or 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
    此时
    -0.92
     dibawah
    -0.89
     mischie
    -0.82
    polated
    -0.79
     potrze
    -0.79
     sorteo
    -0.77
     需要
    -0.75
    位於
    -0.75
    értelmű
    -0.74
    Coef
    -0.73
    POSITIVE LOGITS
     visited
    1.86
     visit
    1.70
    visited
    1.51
    visit
    1.36
     visitar
    1.32
     visiting
    1.30
     visitation
    1.26
     Visited
    1.22
     visite
    1.22
     visitas
    1.21
    Activations Density 0.010%

    No Known Activations