© 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. 71475
    Prev
    Next
    INDEX
    Explanations

    year at Vitesse

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

    The neuron fires strongly on tokens that are either numeric (digits or numbers) or capitalized “named‐entity” words (people, places, dates, etc.).

    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
    RESOURCE
    -1.02
     turisti
    -0.92
     dużo
    -0.87
     reconoc
    -0.85
    iniums
    -0.82
     ま
    -0.82
     РФ
    -0.80
     pog
    -0.80
     mieli
    -0.79
     grupper
    -0.79
    POSITIVE LOGITS
    Mutagenicity
    0.81
    тельности
    0.81
     نداشته
    0.80
    掀
    0.80
     Vulnerability
    0.78
    ','.
    0.77
    のかもしれません
    0.77
    César
    0.76
     investi
    0.76
     дат
    0.73
    Activations Density 0.020%

    No Known Activations