© 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. 10-GEMMASCOPE-RES-131K
    7. 128149
    Prev
    Next
    INDEX
    Explanations

    html/javascript code snippets

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

    The neuron fires on numeric literals (both integer and floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    翃
    -2.64
    苙
    -2.17
    bilden
    -2.03
     greateſt
    -2.03
     leaſt
    -2.02
     kleine
    -1.99
     DONT
    -1.98
    푣
    -1.97
    saus
    -1.96
    〼
    -1.96
    POSITIVE LOGITS
     has
    2.42
     they
    2.34
    </sup>
    2.27
    ⃚
    2.11
    setBold
    2.09
    咴
    2.02
     if
    2.02
    岿
    1.98
    }{
    1.92
    pageY
    1.91
    Activations Density 0.009%

    No Known Activations