© 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. 84103
    Prev
    Next
    INDEX
    Explanations

    containers and components

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

    The neuron is keyed to programming/code context markers—especially script-related tokens (e.g. “<script>” tags, file extensions like .js, folder/bin 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_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
     its
    -0.94
     hilfreich
    -0.91
    lillah
    -0.90
    1
    -0.88
     chong
    -0.86
    2
    -0.86
    咩
    -0.86
     laikā
    -0.86
     aufnehmen
    -0.85
     to
    -0.85
    POSITIVE LOGITS
     beside
    1.11
    VGND
    1.02
     considerar
    0.99
    datable
    0.98
     Any
    0.95
     linge
    0.94
    ativen
    0.94
     desagrad
    0.94
    ỳnh
    0.93
    🏺
    0.92
    Activations Density 0.080%

    No Known Activations