© 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. 34-GEMMASCOPE-RES-131K
    4. 50042
    Prev
    Next
    INDEX
    Explanations

    technical code and systems

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

    This neuron fires on tokens containing digits (e.g. version numbers, dates) or other code‐style numeric references.

    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
    upu
    -0.81
    artner
    -0.79
    奈川
    -0.73
    дравству
    -0.69
    Tomorrow
    -0.69
    enada
    -0.67
    Friend
    -0.66
     커
    -0.66
     betreft
    -0.65
    aky
    -0.64
    POSITIVE LOGITS
     circumstantial
    0.73
     flexibility
    0.70
    alten
    0.69
     dictators
    0.69
     tante
    0.69
    Jep
    0.66
    nij
    0.66
    udder
    0.65
    sslich
    0.65
     perks
    0.64
    Activations Density 0.033%

    No Known Activations