© 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. 34689
    Prev
    Next
    INDEX
    Explanations

    connection parameters

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

    The neuron activates strongly on numeric literal tokens (integer constants) 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
    IPAddress
    -0.84
     localhost
    -0.82
     Collège
    -0.82
    Belly
    -0.81
    リボン
    -0.81
    baseURL
    -0.79
    Configura
    -0.77
    àn
    -0.77
    地址
    -0.77
    undet
    -0.77
    POSITIVE LOGITS
     port
    1.40
     path
    1.16
     Port
    1.05
    path
    0.98
    Port
    0.98
     Path
    0.96
    timeout
    0.95
    port
    0.94
     timeout
    0.92
    端口
    0.91
    Activations Density 0.025%

    No Known Activations