© 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. 108941
    Prev
    Next
    INDEX
    Explanations

    Names ending in iah and el

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

    The neuron activates on proper names (especially biblical‐style male names) containing the sequence “iah.”

    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
    そういう
    -0.76
     dogma
    -0.76
    Ferrari
    -0.76
     পার
    -0.74
     demostr
    -0.73
     metastatic
    -0.72
     swine
    -0.71
    今年は
    -0.71
    Defs
    -0.71
     dey
    -0.70
    POSITIVE LOGITS
    iah
    1.34
    ariah
    1.33
    ías
    1.19
    IAS
    0.98
    athan
    0.96
     Obed
    0.90
    jah
    0.87
    IAH
    0.85
    ÍAS
    0.84
     than
    0.81
    Activations Density 0.036%

    No Known Activations