© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13270
    Prev
    Next
    INDEX
    Explanations

    authentic local or native

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

    The neuron activates on words referring to people or social engagement (e.g. locals, people, meet, authentic experiences).

    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
     annet
    -1.09
    vereign
    -1.06
     خریدار
    -1.01
    ApJ
    -0.99
     marzo
    -0.99
     desde
    -0.98
    丹药
    -0.96
     AIRCRAFT
    -0.96
     ristorante
    -0.96
     atriz
    -0.95
    POSITIVE LOGITS
     authentic
    1.51
    真正的
    1.21
    genu
    1.16
    AUTHENT
    1.14
     authenticate
    1.13
    defines
    1.09
     genuine
    1.07
    Encontra
    1.07
     insider
    1.07
    ohjel
    1.06
    Activations Density 0.016%

    No Known Activations