© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92894
    Prev
    Next
    INDEX
    Explanations

    blood, arterial, cord

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

    references to blood and bodily fluids.

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

    The neuron activates on terms describing blood flow and oxygenation in the circulatory system.

    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
     meint
    -0.80
     einzel
    -0.73
    fis
    -0.69
     mögen
    -0.68
    enty
    -0.66
     Water
    -0.65
     copy
    -0.64
    headers
    -0.64
     header
    -0.63
     landfills
    -0.62
    POSITIVE LOGITS
     blood
    5.69
    blood
    4.03
    Blood
    3.77
     Blood
    3.64
    血
    3.38
     BLOOD
    3.17
     sangre
    3.11
     sangue
    3.02
    BLOOD
    2.98
     خون
    2.80
    Activations Density 0.080%

    No Known Activations