© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130308
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily detecting numeric and Boolean literal tokens (e.g. “0”, “true”, “false”) in code or data contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    health and status correctness

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

    Neuron 4 detects technical content related to numerical values, measurements, or system states, particularly in scientific and technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    植え
    -0.83
     weaker
    -0.83
     ihtiyaç
    -0.80
    равда
    -0.80
     Affected
    -0.80
    язы
    -0.77
    imuth
    -0.77
    ಒ
    -0.75
     nello
    -0.75
     cuál
    -0.74
    POSITIVE LOGITS
     healthy
    1.23
     stable
    1.13
    正常
    1.09
     successful
    1.09
     correct
    1.01
     properly
    0.96
     proper
    0.94
     positiva
    0.92
     normal
    0.91
    保证
    0.91
    Activations Density 0.134%

    No Known Activations