© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59811
    Prev
    Next
    INDEX
    Explanations

    Wnt signaling pathways

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

    numerical identifiers in technical or legal contexts.

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

    The neuron fires on technical alphanumeric identifiers—things like LaTeX style names (newtheoremstyle), gene/pathway names (Wnt1), bus standards (RS-485), and similar model or code labels.

    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
     hushed
    -0.77
     지역
    -0.75
    フー
    -0.67
    يري
    -0.66
    espacio
    -0.63
    ==(
    -0.63
     mantenere
    -0.63
    space
    -0.63
    親
    -0.62
    Cz
    -0.62
    POSITIVE LOGITS
    烷
    0.76
    序列化
    0.72
    chase
    0.68
     foreclosure
    0.68
    nione
    0.66
     dishwasher
    0.66
     densidad
    0.66
     Lösung
    0.66
    🚔
    0.65
     بع
    0.64
    Activations Density 0.061%

    No Known Activations