© 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. 129324
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (standalone numbers, decimals, version/IP/port values) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    network connection strings

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     other
    -1.33
    を
    -1.21
     result
    -1.14
     added
    -1.13
     documents
    -1.12
     address
    -1.11
     details
    -1.09
     others
    -1.09
    と
    -1.09
     staff
    -1.08
    POSITIVE LOGITS
    Aç
    1.35
    ございました
    1.32
    阋
    1.30
     inond
    1.27
    ごめん
    1.26
    えっ
    1.24
    ところに
    1.23
    すみません
    1.19
    verstanden
    1.19
    что
    1.19
    Activations Density 0.025%

    No Known Activations