© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72081
    Prev
    Next
    INDEX
    Explanations

    because, due to, reasons

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

    The neuron is strongly triggered by sentence boundary markers and related discourse cues (periods, ellipses, and connective words like “However” or “Therefore”).

    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
    Potatoes
    -0.93
    Zubereitung
    -0.92
    𝒙
    -0.87
    Dabei
    -0.86
     spil
    -0.81
     rapports
    -0.80
    Beschrijving
    -0.80
    𝒷
    -0.79
    Sein
    -0.79
    Frage
    -0.78
    POSITIVE LOGITS
     devido
    1.27
     debido
    1.21
    因为
    1.10
     потому
    1.09
     aufgrund
    1.07
     بسبب
    1.05
     because
    1.05
     due
    1.04
    因為
    0.99
    由于
    0.91
    Activations Density 0.144%

    No Known Activations