© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106649
    Prev
    Next
    INDEX
    Explanations

    exchange, withdrawal, address

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

    The neuron is a “code‐spotter” – it activates strongly on programming tokens (import paths, identifiers, operators and punctuation in code) rather than on ordinary prose.

    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
     fiori
    -0.77
    dens
    -0.76
    ̭
    -0.75
    RetVal
    -0.72
     megane
    -0.72
     murale
    -0.72
     yaris
    -0.71
     kangoo
    -0.70
    ֆ
    -0.70
    nskap
    -0.69
    POSITIVE LOGITS
     withdrawal
    1.04
     network
    0.96
     withdraw
    0.91
     Networks
    0.89
     Withdrawal
    0.88
     Network
    0.88
     networks
    0.87
    withdrawal
    0.82
     AML
    0.81
     address
    0.79
    Activations Density 0.004%

    No Known Activations