© 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. 34-GEMMASCOPE-RES-131K
    7. 107012
    Prev
    Next
    INDEX
    Explanations

    legal document keywords

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

    The neuron activates on standalone multi‐digit number tokens 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_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
     most
    -1.33
     would
    -1.20
     people
    -1.15
     (
    -1.14
     for
    -1.13
     gave
    -1.13
     not
    -1.12
     did
    -1.10
     do
    -1.09
     as
    -1.08
    POSITIVE LOGITS
     renforcer
    1.08
     unveils
    1.05
    JOH
    1.02
     travailler
    1.00
     taşlı
    0.99
     participer
    0.99
     jednej
    0.98
    Criter
    0.97
     revamped
    0.97
     Advantages
    0.96
    Activations Density 0.018%

    No Known Activations