© 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. 90567
    Prev
    Next
    INDEX
    Explanations

    polio or paralysis

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

    virus-related terminology, especially specific viruses like poliovirus and enterovirus.

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

    The neuron fires strongly on numeric tokens and numeric identifiers (e.g. strain numbers, molecule counts, measurement values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     pollutants
    -0.73
     burner
    -0.73
     iff
    -0.73
     печени
    -0.72
     Groot
    -0.72
    ステ
    -0.72
     alcoholism
    -0.71
     mises
    -0.70
     infar
    -0.70
     Lehre
    -0.70
    POSITIVE LOGITS
     polio
    1.95
     paralysis
    1.12
     paralyzed
    1.05
     Po
    1.00
     paraly
    0.98
     Rotary
    0.97
     Paraly
    0.87
     poli
    0.84
    virus
    0.83
    Po
    0.82
    Activations Density 0.024%

    No Known Activations