© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63118
    Prev
    Next
    INDEX
    Explanations

    scientific classification and numbers

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

    The neuron consistently activates on numeric tokens (counts, measurements, years, and other 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
    Cadastrar
    -0.91
    источник
    -0.85
     Jugendlichen
    -0.85
     Wolfgang
    -0.75
    ilever
    -0.73
    資本
    -0.73
     отобра
    -0.73
    painel
    -0.73
     Perlu
    -0.73
    аз
    -0.72
    POSITIVE LOGITS
     вак
    0.91
    ridescent
    0.76
    oluene
    0.76
    Resumen
    0.75
     dort
    0.75
     verurs
    0.75
     chanteur
    0.73
    asive
    0.72
     mesmer
    0.72
     mów
    0.72
    Activations Density 0.020%

    No Known Activations