© 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. 22-GEMMASCOPE-RES-131K
    7. 40377
    Prev
    Next
    INDEX
    Explanations

    device or apparatus including

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

    The neuron fires strongly on formal, technical noun phrases (e.g. “device,” “apparatus,” “including,” “method”) common in patent-style or specification texts.

    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
    moiselle
    -0.98
    flä
    -0.90
    aneity
    -0.85
     fieldName
    -0.82
     subió
    -0.82
     parceria
    -0.81
    marzo
    -0.79
     detuvo
    -0.78
     homenagem
    -0.77
     quartz
    -0.77
    POSITIVE LOGITS
     satisfactor
    1.02
    车的
    0.96
    你们的
    0.87
    jęcia
    0.85
     zoals
    0.84
    posé
    0.83
    0.83
    脑子
    0.81
    miş
    0.80
    ської
    0.80
    Activations Density 0.008%

    No Known Activations