© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35392
    Prev
    Next
    INDEX
    Explanations

    code snippets and data structures

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

    The neuron activates on numeric tokens and numeric expressions (digits, measurements, and numbers in math).

    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
     and
    -1.11
     sekä
    -1.05
     both
    -1.05
     neither
    -1.00
     zowel
    -0.99
    ifornia
    -0.92
    寺の
    -0.92
     mieszkań
    -0.91
     inspirada
    -0.90
    salomon
    -0.89
    POSITIVE LOGITS
    ac
    0.88
    m
    0.85
    ar
    0.85
    ly
    0.84
     dimin
    0.83
    M
    0.83
    SO
    0.82
    bre
    0.82
    read
    0.82
    SP
    0.81
    Activations Density 0.087%

    No Known Activations