© 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. 92451
    Prev
    Next
    INDEX
    Explanations

    div with class or id

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

    The neuron is specialized in spotting numeric tokens (multi‐digit numbers) wherever they appear.

    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
     preferencias
    -0.88
     aveva
    -0.83
     Versammlung
    -0.77
    puede
    -0.76
     reseñas
    -0.76
    bashrc
    -0.76
     يمكن
    -0.75
     bụng
    -0.74
     alcune
    -0.73
     apropiado
    -0.73
    POSITIVE LOGITS
     class
    1.06
    hidden
    0.91
     for
    0.88
     kvar
    0.79
    piration
    0.78
     beste
    0.77
     Hidden
    0.75
     Penh
    0.75
     Sergio
    0.75
    providedIn
    0.75
    Activations Density 0.004%

    No Known Activations