© 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. 60825
    Prev
    Next
    INDEX
    Explanations

    hypoxia-inducible factor

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

    scientific notations and abbreviations, particularly those related to hypoxia-inducible factor (HIF-1).

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

    The neuron is tuned to pick up mentions of “hypoxia-inducible factor-1” (e.g. HIF-1).

    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
    usd
    -0.71
     noticing
    -0.71
     Asher
    -0.70
    SECURE
    -0.69
     emporio
    -0.69
    miles
    -0.68
     pokoju
    -0.68
     Prid
    -0.67
     Mahler
    -0.67
    meters
    -0.66
    POSITIVE LOGITS
    phytes
    0.88
    hiki
    0.73
    单元
    0.72
    anaf
    0.68
    Bj
    0.67
     Bj
    0.62
    ffè
    0.62
     IFC
    0.61
    каз
    0.61
     Explorer
    0.61
    Activations Density 0.071%

    No Known Activations