© 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. 34-GEMMASCOPE-RES-131K
    7. 81709
    Prev
    Next
    INDEX
    Explanations

    legal and study enumerations

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

    The neuron fires on alphanumeric identifier tokens—short sequences of letters and digits used as technical or case‐ID labels (e.g. “DnaA‐box cluster,” “orf1,” “Court No. 728,” 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_34/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
    riebenen
    -1.00
    𝙧
    -0.93
    ukseen
    -0.90
    лем
    -0.88
     Thirteenth
    -0.85
     ettiği
    -0.84
    skapet
    -0.83
     Eighteenth
    -0.83
     женские
    -0.82
     damaligen
    -0.82
    POSITIVE LOGITS
     II
    3.06
     III
    2.70
    ①
    2.50
     VII
    2.02
     #
    1.99
    II
    1.94
    III
    1.85
     №
    1.84
     \#
    1.80
    １
    1.80
    Activations Density 0.511%

    No Known Activations