© 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. 34-GEMMASCOPE-RES-131K
    7. 2422
    Prev
    Next
    INDEX
    Explanations

    historical figures and concepts

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

    The neuron activates strongly on Latin‐derived or archaic medical/scientific terms and manuscript titles (e.g. “sanitatis,” “Treatise on the Gout,” “cure,” “disseminate”), effectively picking out specialized scholarly vocabulary.

    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
     resale
    -0.89
    brush
    -0.86
    领先
    -0.85
    ＾
    -0.80
    bpm
    -0.80
     légal
    -0.79
     אלה
    -0.79
     brush
    -0.78
     литера
    -0.78
    tricos
    -0.77
    POSITIVE LOGITS
     Galen
    1.13
     conco
    1.05
     naturen
    0.86
     corrupt
    0.85
     Scorpio
    0.84
    यु
    0.83
     egens
    0.81
     Aristotle
    0.81
     corrupted
    0.79
    Mixtures
    0.79
    Activations Density 0.010%

    No Known Activations