© 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. 83978
    Prev
    Next
    INDEX
    Explanations

    C/C++ type declarations

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

    The neuron primarily activates on numeric literals (numbers) in 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
    recycle
    -0.84
     Kathmandu
    -0.74
    ritic
    -0.73
    Gdy
    -0.72
    kı
    -0.72
    Throttle
    -0.70
    alek
    -0.70
    Latex
    -0.70
    getS
    -0.69
    inputData
    -0.69
    POSITIVE LOGITS
     uint
    1.36
     volatile
    1.26
    uint
    1.20
    volatile
    1.05
     volatility
    0.91
    BaseType
    0.82
    mipmap
    0.79
    Platinum
    0.77
    ]:
    
    0.76
    vu
    0.76
    Activations Density 0.016%

    No Known Activations