© 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. 4246
    Prev
    Next
    INDEX
    Explanations

    describing sections

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

    The neuron strongly activates on numeric tokens—especially multi‐digit numbers (e.g. specifications, counts, measurements, prices).

    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
    yum
    -0.93
    lebih
    -0.89
    lox
    -0.83
    ioo
    -0.82
     Temperaturen
    -0.81
     Technologien
    -0.80
     Erişim
    -0.80
     aswell
    -0.79
     Wärme
    -0.78
     spørsmål
    -0.77
    POSITIVE LOGITS
     inhabit
    0.93
     you
    0.91
    This
    0.86
     This
    0.81
     heute
    0.81
    カテゴリ
    0.79
     gerais
    0.79
    CONCLUS
    0.77
    cayaan
    0.75
    ちなみに
    0.75
    Activations Density 0.006%

    No Known Activations