© 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. 752
    Prev
    Next
    INDEX
    Explanations

    English translation

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

    The neuron strongly activates on numerical tokens (e.g. standalone digits, numeric markers, or superscripted numbers).

    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
    avaj
    -0.89
     projek
    -0.86
     Than
    -0.84
    Tá
    -0.81
     Greeks
    -0.80
    projek
    -0.79
    Than
    -0.79
    Agg
    -0.78
     nim
    -0.77
    Owen
    -0.76
    POSITIVE LOGITS
     translators
    1.01
     JET
    1.00
     angiel
    0.95
     English
    0.94
     translated
    0.93
    ộm
    0.93
     tradução
    0.92
     translation
    0.91
    translations
    0.91
     Translated
    0.89
    Activations Density 0.017%

    No Known Activations