© 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. 104914
    Prev
    Next
    INDEX
    Explanations

    category followed by descriptor

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

    The neuron detects mentions of specialized industries, professional services, or formal domains (e.g., “financial services,” “police,” “human rights law,” “telecommunications,” “research,” “metadata,” “evidence”).

    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
     to
    -3.69
     are
    -2.08
     of
    -2.02
     todėl
    -1.71
    !(:
    -1.67
    😆
    -1.65
    💜
    -1.61
    eabouts
    -1.57
     in
    -1.56
    🍻
    -1.54
    POSITIVE LOGITS
     cueva
    2.19
     jaula
    2.14
     gastronomía
    1.88
     alfombra
    1.87
     naszej
    1.85
     araña
    1.85
     vientre
    1.83
     lámpara
    1.83
     estufa
    1.83
     acuario
    1.80
    Activations Density 0.295%

    No Known Activations