© 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. 107618
    Prev
    Next
    INDEX
    Explanations

    siderophores, siderosomes, siderosis

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

    The neuron detects variations of the word "sider" including "siderosis," "siderosomes," and "SIDEROS" in scientific and technical contexts.

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

    This neuron is highly sensitive to the character sequence “sider” appearing inside tokens.

    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
    ⅖
    -0.75
     Preparatory
    -0.73
    Gabri
    -0.69
    лку
    -0.68
    Independence
    -0.68
     purifying
    -0.68
     ܘ
    -0.68
    Salam
    -0.67
    ή
    -0.67
     drafted
    -0.66
    POSITIVE LOGITS
     Lan
    0.75
     Appendix
    0.68
    MLS
    0.67
    bak
    0.67
     multiple
    0.63
    ﾌ
    0.63
     bold
    0.62
     Cameron
    0.62
    bem
    0.62
    肝
    0.62
    Activations Density 0.069%

    No Known Activations