© 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. 10-GEMMASCOPE-RES-131K
    7. 87060
    Prev
    Next
    INDEX
    Explanations

    ports and numbers

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

    The neuron activates on numeric tokens—especially multi‐digit sequences like port numbers or other configuration values.

    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
     new
    -1.94
     also
    -1.75
     as
    -1.66
    新的
    -1.56
     in
    -1.54
     with
    -1.45
     work
    -1.37
     through
    -1.34
     In
    -1.33
     could
    -1.33
    POSITIVE LOGITS
     murm
    1.42
     tuto
    1.38
     ？
    1.37
    龇
    1.34
    .」
    1.31
    👣
    1.30
     Traité
    1.28
     noter
    1.27
    Recher
    1.27
     thefe
    1.26
    Activations Density 0.107%

    No Known Activations