© 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. 102452
    Prev
    Next
    INDEX
    Explanations

    official names and places

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

    The neuron strongly activates on numeric tokens (digits and numbers) in the text.

    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
    Matériau
    -0.97
     Kut
    -0.89
    Somos
    -0.85
    حه
    -0.77
     Gerais
    -0.75
    दो
    -0.73
    Kut
    -0.71
     mammoth
    -0.71
    Galería
    -0.70
     bereits
    -0.69
    POSITIVE LOGITS
     Website
    1.03
    Website
    1.02
    Typical
    0.95
     Typical
    0.92
     Notable
    0.91
    typical
    0.90
     website
    0.89
    Notable
    0.86
    influenced
    0.84
     WEBSITE
    0.84
    Activations Density 0.125%

    No Known Activations