© 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. 10-GEMMASCOPE-RES-131K
    4. 105245
    Prev
    Next
    INDEX
    Explanations

    metabolism, glucose, and lactate

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

    This neuron identifies scientific content related to metabolism, particularly detecting terms like "energy", "glycolysis", "acid", "glucose", and other metabolic processes in academic medical and biochemical texts.

    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_10/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
    izações
    -1.33
    cześ
    -1.30
     parro
    -1.30
    ೢ
    -1.24
    ϳ
    -1.22
    brtc
    -1.22
     projetos
    -1.21
    蟜
    -1.20
    鵙
    -1.20
     Mbps
    -1.16
    POSITIVE LOGITS
     for
    1.53
     during
    1.45
     not
    1.34
    Other
    1.30
     second
    1.30
     other
    1.28
     adequate
    1.28
     this
    1.26
     TWO
    1.23
    Two
    1.23
    Activations Density 0.540%

    No Known Activations