© 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. 45301
    Prev
    Next
    INDEX
    Explanations

    awards and presentations

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

    The neuron strongly activates on numeric expressions—including raw digits, dates, monetary amounts, and related tokens.

    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
    やお
    -0.80
    тування
    -0.79
    ansvar
    -0.79
    ampire
    -0.79
    hello
    -0.75
     impati
    -0.71
     глазами
    -0.71
    reviewed
    -0.71
    আ
    -0.70
    혹
    -0.69
    POSITIVE LOGITS
     presentation
    2.34
     certificate
    2.22
     presented
    2.03
     plaque
    1.97
     Certificate
    1.86
     certificates
    1.86
     presentations
    1.83
    presentation
    1.80
     presenting
    1.75
    Presentation
    1.70
    Activations Density 0.030%

    No Known Activations