© 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. 73688
    Prev
    Next
    INDEX
    Explanations

    listing cast, personnel, leaders, and requirements

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

    The neuron fires on standalone document section headings or labels (e.g., “Requirements,” “Candidate profile,” “Nearest settlements,” “Statistical leaders,” “Skills and Requirements,” “Who you are,” “Personnel,” “Risk factors”).

    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
     kérdés
    -1.30
    ↵↵
    -1.24
    不明白
    -1.16
     provenientes
    -1.12
     prioridad
    -1.11
     observación
    -1.07
     Bildschirm
    -1.06
     แต่
    -1.05
     flera
    -1.05
     Unterschiede
    -1.03
    POSITIVE LOGITS
     his
    1.56
    :
    
    1.55
     including
    1.41
    Two
    1.40
     six
    1.29
     two
    1.29
    Being
    1.26
    Going
    1.23
     includes
    1.23
    Following
    1.22
    Activations Density 0.001%

    No Known Activations