© 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. 70210
    Prev
    Next
    INDEX
    Explanations

    separate, separately, individually

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

    The neuron fires on numeric tokens (any standalone number or digit sequence) 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
    乃至
    -0.84
    某些
    -0.80
    MenuGroup
    -0.79
     Trauer
    -0.77
     framför
    -0.76
    ब्द
    -0.75
     insbesondere
    -0.72
     harán
    -0.71
    IKit
    -0.71
     Herbst
    -0.71
    POSITIVE LOGITS
     separate
    7.78
     separately
    6.66
    separate
    6.56
    Separate
    6.06
     Separate
    5.81
     seperate
    5.50
     отдель
    5.13
     SEPAR
    5.13
    Separ
    4.94
    separ
    4.84
    Activations Density 0.351%

    No Known Activations