© 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. 22-GEMMASCOPE-RES-131K
    7. 35232
    Prev
    Next
    INDEX
    Explanations

    common surnames in author lists

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

    The neuron strongly activates on capitalized personal names—especially last names—in author bylines and reference lists.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     different
    -1.25
     without
    -1.20
     as
    -1.20
     while
    -1.16
     like
    -1.13
     after
    -1.13
    弊社
    -1.13
     only
    -1.12
     is
    -1.12
     any
    -1.11
    POSITIVE LOGITS
     และ
    1.25
     parfois
    1.21
    oluble
    1.13
     lanç
    1.13
    ppincott
    1.12
    ַּ
    1.11
     enfance
    1.10
     réinitial
    1.09
     COLD
    1.09
    },
    1.08
    Activations Density 0.033%

    No Known Activations