© 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. 22-GEMMASCOPE-RES-131K
    4. 68933
    Prev
    Next
    INDEX
    Explanations

    product specifications

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

    The neuron detects standalone field labels or section headings (e.g. single words like “Yes,” “References,” “Brand,” “Condition,” “Age,” “Group”) used to mark attributes in resumes or product/specification listings.

    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
    Atentamente
    -0.92
     faç
    -0.92
     changed
    -0.91
    όνι
    -0.90
     heard
    -0.90
     so
    -0.90
    Únete
    -0.86
     черво
    -0.85
    ландия
    -0.84
    七月
    -0.83
    POSITIVE LOGITS
     seller
    1.23
    ﻻ
    1.16
    ἵ
    1.09
    集体
    1.05
     élégant
    1.05
     Wigan
    1.03
     product
    1.02
    𝑈
    1.01
    ssize
    1.01
     item
    0.98
    Activations Density 0.003%

    No Known Activations