© 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. 98229
    Prev
    Next
    INDEX
    Explanations

    introductions and questions

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

    The neuron fires on title‐cased words and phrases—proper names and titles (e.g. book or section headings).

    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
     ∼
    -0.69
    Fourier
    -0.69
    ulin
    -0.67
    厲
    -0.65
    ūra
    -0.65
    CharStream
    -0.64
    論
    -0.64
    Deserialize
    -0.64
    ‍♀️
    -0.63
     کی
    -0.63
    POSITIVE LOGITS
     Aristotle
    0.99
     concrete
    0.90
    Optimis
    0.89
    Aristotle
    0.86
     epist
    0.86
     LGBTQ
    0.84
     readers
    0.83
    ORDON
    0.82
     playlist
    0.81
     Kubernetes
    0.81
    Activations Density 0.028%

    No Known Activations