© 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. 48385
    Prev
    Next
    INDEX
    Explanations

    organizations and standards

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

    The neuron zeroes in on numeric and quantitative expressions—digits, percentages, measurements, and related symbols.

    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
     TBD
    -0.93
     ONG
    -0.85
     GHG
    -0.85
     kWh
    -0.84
     TTS
    -0.83
    ography
    -0.81
     Appellants
    -0.80
     VFX
    -0.79
     Corollary
    -0.79
     precies
    -0.78
    POSITIVE LOGITS
     National
    1.98
     USDA
    1.80
     Federal
    1.64
    National
    1.60
     FDA
    1.55
     NCAA
    1.51
     IEEE
    1.50
     federal
    1.43
     ISO
    1.34
     EPA
    1.34
    Activations Density 0.364%

    No Known Activations