© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118118
    Prev
    Next
    INDEX
    Explanations

    iron and metals

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

    words related to iron compounds and minerals in medical and biochemical contexts.

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

    The neuron strongly activates on mentions of iron and iron‐related biology—e.g. iron metabolism, heme, ferritin, transfusion dependence, and iron‐chelation therapy.

    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
    zkę
    -0.82
    ethereum
    -0.75
     Pila
    -0.73
    AddColumn
    -0.73
     trò
    -0.72
     street
    -0.71
     rigging
    -0.70
     Lido
    -0.70
    ラグ
    -0.69
    kene
    -0.69
    POSITIVE LOGITS
     iron
    2.59
    Iron
    2.11
     Iron
    2.05
    iron
    2.03
    IRON
    1.77
     IRON
    1.63
    铁
    1.48
     желе
    1.41
     irons
    1.41
    鉄
    1.37
    Activations Density 0.117%

    No Known Activations