© 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. 10-GEMMASCOPE-RES-131K
    7. 85902
    Prev
    Next
    INDEX
    Explanations

    Names of people

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

    The neuron detects personal names (proper names of people) in the 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_10/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
    ærke
    -1.09
    ,
    -1.08
    ܜ
    -1.05
     amikor
    -1.05
    мам
    -1.04
     actuelles
    -1.02
    coment
    -1.02
    wachsenen
    -1.01
     Later
    -1.01
     ambos
    -1.00
    POSITIVE LOGITS
    ります
    1.41
     actually
    1.38
    ίζει
    1.26
     really
    1.24
    お願いします
    1.22
     móg
    1.20
     truly
    1.20
     realmente
    1.18
    ICULO
    1.17
    စ်
    1.16
    Activations Density 0.152%

    No Known Activations