© 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. 34-GEMMASCOPE-RES-131K
    4. 75833
    Prev
    Next
    INDEX
    Explanations

    clock generation and recovery

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

    The neuron consistently fires on code- or documentation-level mentions of “clk” or “clock” (e.g. clock-related identifiers, includes, APIs, and frequency values).

    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
    entendre
    -0.83
     ambush
    -0.82
    readString
    -0.78
    :……
    -0.78
    orton
    -0.76
    swald
    -0.75
    쯔
    -0.75
    organisation
    -0.75
     khoai
    -0.75
    bolt
    -0.73
    POSITIVE LOGITS
     source
    1.06
     sources
    1.01
     distribution
    0.84
    源
    0.83
     divided
    0.82
    source
    0.82
    divided
    0.80
     src
    0.80
    ÷
    0.79
     getSource
    0.77
    Activations Density 0.018%

    No Known Activations