© 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. 71012
    Prev
    Next
    INDEX
    Explanations

    network speeds and technologies

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

    This neuron activates on numeric tokens (including numbers with units) that specify technical measurements such as speeds, capacities, and data-rates.

    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
     NSCoder
    -1.15
     "..\..\..\
    -1.11
     doInBackground
    -1.09
     desmotiv
    -1.07
     escond
    -1.07
     invokevirtual
    -1.06
     ovos
    -1.05
    瘴
    -1.05
     Königin
    -1.05
    ijakan
    -1.05
    POSITIVE LOGITS
     speeds
    1.66
     capabilities
    1.21
     speed
    1.21
    from
    1.17
    oció
    1.16
     isn
    1.13
     nettement
    1.09
     ännu
    1.09
    speed
    1.06
     capability
    1.05
    Activations Density 0.027%

    No Known Activations