© 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. 6814
    Prev
    Next
    INDEX
    Explanations

    up to

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

    The neuron strongly activates on the collocation “up to,” i.e. instances of “up” immediately followed by “to.”

    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
    ې
    -0.94
     karier
    -0.93
    Secara
    -0.88
    ánicos
    -0.84
     gier
    -0.83
     lâng
    -0.80
    goBack
    -0.80
    IZAR
    -0.79
    Demikian
    -0.78
     kopp
    -0.77
    POSITIVE LOGITS
     up
    4.84
     upto
    3.25
    upto
    2.34
    Up
    2.22
     Up
    1.98
    up
    1.70
     lên
    1.60
     to
    1.41
     até
    1.34
     вверх
    1.27
    Activations Density 0.024%

    No Known Activations