© 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. 10-GEMMASCOPE-RES-131K
    7. 105125
    Prev
    Next
    INDEX
    Explanations

    CPU count, time, core

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

    the acronym "CPU" and related technical terms for central processing unit.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on mentions of CPUs together with their numeric values (e.g. “CPU Count”, “CPU %”, or similar CPU-related measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Then
    -2.83
    、“
    -2.81
    .“
    -2.75
    “
    -2.67
     (“
    -2.63
    ."
    -2.48
    谖
    -2.41
     —
    -2.39
    ,“
    -2.36
     Sadly
    -2.36
    POSITIVE LOGITS
     cruzado
    2.38
    er
    2.33
     OGSÅ
    2.31
    wyczaj
    2.23
     exakt
    2.20
     ४
    2.17
     aidé
    2.16
    in
    2.14
     trong
    2.13
    section
    2.11
    Activations Density 0.009%

    No Known Activations