© 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. 115954
    Prev
    Next
    INDEX
    Explanations

    specific numbers and labels

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

    The neuron is primarily detecting numeric tokens or reference codes (e.g. years, enumeration markers, page/article 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
     ни
    -0.84
    inete
    -0.83
    ABBRE
    -0.79
    onan
    -0.77
     nama
    -0.77
     원
    -0.76
     PLoS
    -0.75
     Sammlung
    -0.75
    ereza
    -0.74
     sinus
    -0.74
    POSITIVE LOGITS
    Zusammenfassung
    0.83
     Pilihan
    0.78
     Meksi
    0.78
     Apalagi
    0.78
    žo
    0.77
     Även
    0.77
     Meski
    0.76
     levert
    0.75
     halve
    0.75
     Ziele
    0.75
    Activations Density 0.015%

    No Known Activations