© 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. 50434
    Prev
    Next
    INDEX
    Explanations

    package import (

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

    The neuron is highly activated by numeric literal tokens (i.e. numbers) in source code.

    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
     from
    -1.05
     their
    -1.02
     only
    -0.94
    薦
    -0.85
     various
    -0.85
     now
    -0.84
     confused
    -0.84
     both
    -0.82
     more
    -0.81
     there
    -0.80
    POSITIVE LOGITS
     aident
    0.92
    obox
    0.92
    ‘‘
    0.91
    никам
    0.90
    aminen
    0.89
    laim
    0.88
    itself
    0.86
    among
    0.84
     verborgen
    0.83
    )”
    0.82
    Activations Density 0.025%

    No Known Activations