© 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. 13711
    Prev
    Next
    INDEX
    Explanations

    person names

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

    This neuron detects numeric tokens—especially years, dates, ages, or other digit strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    biographical or memorial content with dates, names, and life events.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of named entities—especially personal names, dates/years, ages, and academic credentials in formal biographical or obituary-style text.

    oai_token-act-pair · gpt-5Triggered 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
    īb
    -0.97
    StartCoroutine
    -0.93
    convertView
    -0.93
    abancı
    -0.93
    它们
    -0.92
     ontstaan
    -0.90
     olev
    -0.88
     selva
    -0.87
    cetak
    -0.87
     Parte
    -0.86
    POSITIVE LOGITS
     our
    1.38
     Producto
    1.13
     atualizar
    1.07
    
    1.05
     classmate
    1.04
     همچ
    1.02
     brilho
    1.00
    ственную
    0.99
     skvě
    0.98
     zmieni
    0.98
    Activations Density 0.003%

    No Known Activations