© 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. 60810
    Prev
    Next
    INDEX
    Explanations

    cal, Cali, calcineurin

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

    Neuron 4 detects technical or scientific terms, particularly related to biological or medical compounds like calcineurin and immunosuppressants.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is responding to numbers and numeric sequences (e.g. years, dates, and other digit strings).

    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
    NR
    -0.80
    Code
    -0.77
    لية
    -0.73
     テラス
    -0.70
     stanga
    -0.68
     Teknologi
    -0.67
     quadrature
    -0.67
     христиан
    -0.67
     categoria
    -0.67
    ampu
    -0.67
    POSITIVE LOGITS
     cal
    2.92
     Cali
    2.78
    Cali
    2.53
    cal
    2.02
     CAL
    1.88
     Cal
    1.77
    CAL
    1.70
     Calif
    1.68
    Cal
    1.59
     cali
    1.55
    Activations Density 0.034%

    No Known Activations