© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128624
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently fires on numeric tokens (sequences of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    connecting items

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     resa
    -0.90
     groei
    -0.88
     facets
    -0.87
    estimable
    -0.87
     grava
    -0.86
    𝚘
    -0.84
    我们需要
    -0.84
    ônes
    -0.84
    えたら
    -0.83
    temporada
    -0.83
    POSITIVE LOGITS
    </h4>
    0.94
    Składniki
    0.84
     complement
    0.81
     типи
    0.77
    Complement
    0.76
     éve
    0.75
    俳
    0.75
     élimin
    0.74
    Excluir
    0.73
    
    0.73
    Activations Density 0.294%

    No Known Activations