© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35626
    Prev
    Next
    INDEX
    Explanations

    simultaneous or separate actions

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

    The neuron activates on numeric tokens—i.e. it flags numbers or numeric literals 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_22/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
    THEME
    -0.95
    bufio
    -0.91
    usleep
    -0.82
    زندگی
    -0.81
     vindo
    -0.79
    themed
    -0.79
     forskellige
    -0.79
    賤
    -0.78
     special
    -0.78
     freshly
    -0.77
    POSITIVE LOGITS
    同時に
    0.99
    simult
    0.98
     separate
    0.90
     separately
    0.88
     отдельно
    0.88
     面包
    0.87
     simultaneous
    0.86
     simultaneously
    0.85
     одновременно
    0.85
     included
    0.84
    Activations Density 0.018%

    No Known Activations