© 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. 13727
    Prev
    Next
    INDEX
    Explanations

    such as

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

    The neuron fires on numeric tokens (e.g. years, section/file numbers) 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
     infographic
    -1.79
    https
    -1.79
     selfie
    -1.75
     microbiome
    -1.71
     ২০১
    -1.67
     YouTuber
    -1.64
     ۲۰۱
    -1.61
     livestream
    -1.60
     hashtag
    -1.59
     https
    -1.58
    POSITIVE LOGITS
     both
    1.80
     idéia
    1.66
     eight
    1.65
     seven
    1.55
     dazzling
    1.54
     adequate
    1.48
     nine
    1.47
     considerably
    1.47
     five
    1.45
     substantially
    1.45
    Activations Density 0.385%

    No Known Activations