© 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. 22-GEMMASCOPE-RES-131K
    7. 75275
    Prev
    Next
    INDEX
    Explanations

    technical and scientific entities

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

    The neuron fires on formal or technical keywords—things like legal‐entity terms (limited, liability, company), code identifiers (java, view, Benchmark_Result), and specialized scientific nomenclature (peptides, hydrazides).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ме
    -1.06
     spéciaux
    -1.02
     flesta
    -1.00
     Perspek
    -1.00
     spécialisée
    -0.98
     Вы
    -0.97
     arrêter
    -0.96
     Ă
    -0.95
    する
    -0.94
     neuve
    -0.94
    POSITIVE LOGITS
     ``
    1.22
    ਫ਼
    1.17
    Lá
    1.16
    Rozmiar
    1.11
    过来了
    1.11
     Ofrece
    1.09
    ）」
    1.07
    Доставка
    1.06
     wrze
    1.05
     })
    1.05
    Activations Density 0.071%

    No Known Activations