© 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. 54090
    Prev
    Next
    INDEX
    Explanations

    associated with medical conditions and biological processes

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

    terms associated with scientific or academic subjects in context.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on prominent domain-specific technical terms—i.e. the key content-bearing nouns and adjectives that signal a specialized topic.

    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
     for
    -1.07
     exemplo
    -1.06
     to
    -1.05
    の中から
    -0.98
     gemeinsam
    -0.95
     usando
    -0.93
     takiego
    -0.92
     ExecuteAsync
    -0.91
     último
    -0.91
     convenable
    -0.91
    POSITIVE LOGITS
    haften
    1.05
     pilares
    0.98
    klinik
    0.96
    Baik
    0.96
    ländern
    0.94
     pesados
    0.93
     bicicletas
    0.91
    tentu
    0.91
    而言
    0.90
    frust
    0.90
    Activations Density 0.163%

    No Known Activations