© 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. 55789
    Prev
    Next
    INDEX
    Explanations

    cold storage

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

    The neuron is triggered by numeric literals (tokens containing digits).

    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
     viewDidLoad
    -0.75
    idr
    -0.74
     BSEB
    -0.73
    وئ
    -0.73
     SID
    -0.71
     recently
    -0.71
     villaggio
    -0.70
     ರ
    -0.70
     Carrefour
    -0.70
     Pollock
    -0.69
    POSITIVE LOGITS
     platforms
    1.08
     platform
    1.05
    platforms
    0.97
     Platform
    0.93
     Platforms
    0.88
     entorno
    0.87
     dimensions
    0.87
     Dimensions
    0.87
    Platform
    0.86
    platform
    0.85
    Activations Density 0.002%

    No Known Activations