© 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. 90363
    Prev
    Next
    INDEX
    Explanations

    proposed publication

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

    The neuron fires on the characteristic phrasing of formal definitions—especially the “X is the Y that…” pattern introducing and defining technical terms.

    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
     reciente
    -1.19
     Recently
    -1.08
     recenti
    -1.06
     exemplos
    -1.05
     récemment
    -1.05
     recently
    -1.04
    ⌀
    -1.03
    recently
    -1.02
    ७
    -0.99
    ८
    -0.98
    POSITIVE LOGITS
     later
    1.55
     seminal
    1.36
     landmark
    1.31
     published
    1.29
     publication
    1.26
     publish
    1.25
     pioneering
    1.20
     subsequent
    1.17
    refined
    1.16
     his
    1.13
    Activations Density 0.132%

    No Known Activations