© 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. 22-GEMMASCOPE-RES-131K
    4. 74950
    Prev
    Next
    INDEX
    Explanations

    optical filters and speeds

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

    The neuron strongly activates on subword fragments that form part of technical or scientific terminology (e.g. roots of specialized jargon).

    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
     only
    -0.90
     just
    -0.88
     time
    -0.85
     well
    -0.84
    ’
    -0.83
     each
    -0.82
     you
    -0.82
     another
    -0.81
    :
    -0.80
     very
    -0.79
    POSITIVE LOGITS
    ֟
    1.05
     ファッション
    0.88
    闼
    0.86
     nabízí
    0.85
     infest
    0.84
    􏿿
    0.84
     assures
    0.82
    /**
    
    
    0.82
     حيث
    0.81
    onii
    0.81
    Activations Density 0.507%

    No Known Activations