© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111087
    Prev
    Next
    INDEX
    Explanations

    folks who

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

    The main thing this neuron does is detect occurrences of the informal address “folks.”

    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
     usamos
    -2.47
    ᾠ
    -2.28
    蕺
    -2.25
     preguntar
    -2.20
     кольца
    -2.19
    皛
    -2.06
    驺
    -2.06
    çok
    -2.06
     acoged
    -2.05
     impediment
    -2.05
    POSITIVE LOGITS
    n
    2.84
    寕
    2.55
    ta
    2.48
    色が
    2.39
     berdua
    2.31
    菔
    2.28
    al
    2.25
    ?”
    2.20
     fashioned
    2.17
    is
    2.16
    Activations Density 0.004%

    No Known Activations