© 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. 116272
    Prev
    Next
    INDEX
    Explanations

    names followed by initials or middle names

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

    The neuron detects capitalized personal names (proper given names) in text.

    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
    の方に
    -1.17
     alten
    -1.08
     our
    -1.04
     digno
    -1.02
    ambut
    -1.01
     нынеш
    -1.00
     lanzado
    -0.98
     cómoda
    -0.97
    机遇
    -0.96
     outra
    -0.95
    POSITIVE LOGITS
    哽
    1.02
    핼
    0.99
    сть
    0.88
    😥
    0.86
     manhattan
    0.85
     hdd
    0.85
     diy
    0.84
    巴士
    0.82
    显
    0.82
     bauer
    0.82
    Activations Density 0.023%

    No Known Activations