© 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. 128901
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric literals (tokens consisting of digits).

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

    conditional logic

    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
    といいます
    -0.98
     ͡
    -0.90
    Сообщение
    -0.86
    といい
    -0.85
    voici
    -0.85
    возможно
    -0.85
     berkom
    -0.84
     interactiva
    -0.83
     gouvernement
    -0.83
    と感じ
    -0.82
    POSITIVE LOGITS
     otherwise
    1.24
    else
    0.99
     else
    0.99
    否则
    0.89
     Otherwise
    0.86
    Imm
    0.85
     if
    0.81
     иначе
    0.79
    Redux
    0.78
     variante
    0.77
    Activations Density 0.008%

    No Known Activations