© 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. 30872
    Prev
    Next
    INDEX
    Explanations

    middle initial or monogram

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

    The neuron detects mentions of a person’s middle name or middle initial (including double-barrelled or initial forms).

    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
    rih
    -0.78
    Inn
    -0.77
    ensemble
    -0.73
    いです
    -0.72
    lamento
    -0.71
     भाषा
    -0.71
    Mux
    -0.71
    훼
    -0.70
     Xerox
    -0.70
    issens
    -0.68
    POSITIVE LOGITS
     initials
    5.50
     Initi
    3.52
    Initi
    3.44
    initi
    3.38
     initial
    3.02
     initi
    2.92
     иници
    2.83
     Initial
    2.56
     iniciales
    2.55
    initial
    2.52
    Activations Density 0.041%

    No Known Activations