© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72059
    Prev
    Next
    INDEX
    Explanations

    model"The" before noun phrases

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

    The neuron detects numeric literals—any standalone numbers (integers or decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ghế
    -1.16
    Vå
    -1.11
     úteis
    -1.08
     feitas
    -1.08
     intelligente
    -1.06
     asseg
    -1.05
    蚰
    -1.05
    
    -1.05
     návště
    -1.04
     caucho
    -1.01
    POSITIVE LOGITS
     only
    1.15
     just
    1.02
     already
    1.00
     work
    0.93
     not
    0.88
     purely
    0.84
     with
    0.84
     even
    0.82
     completely
    0.80
     simply
    0.77
    Activations Density 0.005%

    No Known Activations