© 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. 90331
    Prev
    Next
    INDEX
    Explanations

    numbers and licenses

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

    The neuron responds to numeric tokens (i.e. sequences of digits, such as page numbers, years, and citation numbers).

    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
     SAMPLE
    -0.75
     Iman
    -0.73
     tuples
    -0.71
     Reducer
    -0.69
    Contained
    -0.68
    lyn
    -0.66
     SYS
    -0.66
    umumkan
    -0.65
     Analyzer
    -0.62
    Reducer
    -0.61
    POSITIVE LOGITS
     (~
    0.74
     Bad
    0.63
    Bad
    0.63
     Wyn
    0.62
    RunAsync
    0.61
     Panel
    0.60
     επικ
    0.60
     stab
    0.60
    CascadeType
    0.60
     ExecuteAsync
    0.60
    Activations Density 0.077%

    No Known Activations