© 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. 34-GEMMASCOPE-RES-131K
    4. 33131
    Prev
    Next
    INDEX
    Explanations

    growth factors and regulators

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

    The neuron detects the word "growth" and related concepts in scientific contexts, particularly related to biological development and cell proliferation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    seeded
    -0.84
     MANUAL
    -0.80
     выращи
    -0.78
    髅
    -0.77
    ocular
    -0.76
     manu
    -0.76
    ViewImports
    -0.75
     Portal
    -0.75
     Crom
    -0.75
    Portal
    -0.75
    POSITIVE LOGITS
     conditions
    1.05
     regulators
    0.95
    Informações
    0.87
    Opinión
    0.84
     Conditions
    0.83
    Índice
    0.80
     regulator
    0.80
     habits
    0.79
    Música
    0.78
    Nuevas
    0.77
    Activations Density 0.044%

    No Known Activations