© 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. 34500
    Prev
    Next
    INDEX
    Explanations

    `max-`, `pinconf-`, `import/`

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

    The neuron is highly activated by numeric literals (digit sequences) in source code.

    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
     kopling
    -1.08
     pintada
    -1.02
     estampado
    -0.98
     espagnol
    -0.97
    喊道
    -0.96
     vegano
    -0.92
    ▨
    -0.91
     estampada
    -0.91
    grandfather
    -0.90
     veuillez
    -0.90
    POSITIVE LOGITS
    QUÉ
    1.00
     اليمن
    0.85
     ANYTHING
    0.84
     impromptu
    0.83
    ान
    0.76
    EXAMPLES
    0.75
     Thunderbird
    0.75
     IRR
    0.75
    bü
    0.73
     recie
    0.73
    Activations Density 0.110%

    No Known Activations