© 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. 8345
    Prev
    Next
    INDEX
    Explanations

    study followed by findings

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

    The neuron mainly detects numeric measurement values (multi‐digit numbers) in scientific or technical contexts.

    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
    baş
    -0.94
     السياس
    -0.94
     transitioning
    -0.93
    ита
    -0.93
     külön
    -0.93
     memiliki
    -0.91
     JLabel
    -0.89
     jedynie
    -0.89
    варя
    -0.89
    ază
    -0.88
    POSITIVE LOGITS
     appeared
    0.92
     investigates
    0.90
     weitgehend
    0.90
     möglichst
    0.89
     investigate
    0.88
     affords
    0.87
     slop
    0.86
     occupies
    0.84
     coincide
    0.84
     regarded
    0.83
    Activations Density 0.038%

    No Known Activations