© 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. 34-GEMMASCOPE-RES-131K
    4. 93938
    Prev
    Next
    INDEX
    Explanations

    first names

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

    The neuron detects personal proper names (people’s first names).

    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
     that
    -1.12
     on
    -1.10
     gitara
    -1.09
    حوال
    -1.09
     in
    -1.09
     camisetas
    -1.05
    Lá
    -1.02
    石垣
    -1.02
     this
    -1.02
    pires
    -1.01
    POSITIVE LOGITS
    ·
    1.30
     himself
    1.29
    andering
    1.27
     نفسه
    1.25
    驟
    1.24
    nment
    1.17
    ;</
    1.16
     intric
    1.16
    LY
    1.15
    licitations
    1.13
    Activations Density 0.073%

    No Known Activations