© 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. 22-GEMMASCOPE-RES-131K
    7. 35709
    Prev
    Next
    INDEX
    Explanations

    git branch, springframework, encoding

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

    The neuron is essentially a number‐detector—it fires on tokens that are numeric quantities.

    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
    tissement
    -0.85
     fizeram
    -0.82
    make
    -0.81
    _
    -0.81
     informou
    -0.79
    Fault
    -0.79
     два
    -0.79
     verspre
    -0.79
    ior
    -0.78
     tiveram
    -0.78
    POSITIVE LOGITS
    cussed
    0.93
     svi
    0.93
     minas
    0.90
     ilgi
    0.90
     okam
    0.88
     meus
    0.88
     AÑOS
    0.85
     guardi
    0.85
     tvor
    0.84
     antigua
    0.83
    Activations Density 0.017%

    No Known Activations