© 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. 10-GEMMASCOPE-RES-131K
    7. 90295
    Prev
    Next
    INDEX
    Explanations

    business and service terms

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

    The neuron activates on multi‐word proper names and other named entities (e.g. company names, court titles, party names, postal districts) 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_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
     parámetros
    -1.89
     impresora
    -1.88
     gastronomía
    -1.86
     çünkü
    -1.84
     prends
    -1.80
     ruido
    -1.75
     guapos
    -1.75
     särsk
    -1.73
    lanır
    -1.70
     optimizar
    -1.70
    POSITIVE LOGITS
     in
    2.27
     also
    2.13
     including
    2.06
    𝒙
    1.88
     of
    1.84
    .
    1.79
    єр
    1.54
    contentValues
    1.53
    җ
    1.52
     mehr
    1.45
    Activations Density 0.023%

    No Known Activations