© 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. 34-GEMMASCOPE-RES-131K
    7. 108794
    Prev
    Next
    INDEX
    Explanations

    calcitonin, calcification, calcitriol

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

    medical terms related to calcium and calcitonin.

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

    The neuron strongly responds to the character sequence “calc,” i.e. words or subwords beginning with “calc” (e.g. calcitriol, calcification, paricalcitol).

    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
    设立
    -0.75
    mā
    -0.72
     bibl
    -0.71
     grouping
    -0.71
     Ernährung
    -0.71
    oston
    -0.69
    ISHI
    -0.69
    frig
    -0.69
    ātu
    -0.68
    ciences
    -0.67
    POSITIVE LOGITS
    cie
    0.80
    sibirsk
    0.77
    omycin
    0.77
    ined
    0.74
     Keating
    0.74
    Bluetooth
    0.74
     Krueger
    0.71
    ified
    0.71
    atoire
    0.70
    typed
    0.69
    Activations Density 0.034%

    No Known Activations