© 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. 67898
    Prev
    Next
    INDEX
    Explanations

    to followed by an action verb

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

    The neuron fires on numeric tokens – it picks out numbers (years, version numbers, section or rule numbers, etc.) in the text.

    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
     their
    -2.48
     all
    -2.08
     more
    -2.02
     helps
    -1.90
     an
    -1.87
     first
    -1.85
     so
    -1.84
     one
    -1.81
     every
    -1.78
     two
    -1.76
    POSITIVE LOGITS
     .......
    1.86
     Dinas
    1.77
     .........
    1.76
    튿
    1.64
     ..........
    1.64
     🥰
    1.62
     CURRENT
    1.62
     ........
    1.61
     フリル
    1.61
     ludicrous
    1.58
    Activations Density 0.053%

    No Known Activations