© 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. 116241
    Prev
    Next
    INDEX
    Explanations

    vasoactive, vasodilator, vasopressin

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

    The neuron detects medical terms related to blood vessels, particularly words starting with "vas" like "vasoactive," "vasodilators," and "vasopressin."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     anest
    -0.91
    follows
    -0.91
     fundos
    -0.86
     ISNI
    -0.85
    FOLLOW
    -0.83
     aspi
    -0.83
    },[])
    -0.82
     fiestas
    -0.82
     singularities
    -0.81
     quartos
    -0.80
    POSITIVE LOGITS
    quez
    0.91
     later
    0.90
    ৌ
    0.83
    Vas
    0.83
     precipit
    0.79
     suelen
    0.77
     Vas
    0.76
    later
    0.75
    universal
    0.73
    解散
    0.73
    Activations Density 0.026%

    No Known Activations