© 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. 33710
    Prev
    Next
    INDEX
    Explanations

    citations and references

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

    The neuron primarily detects numeric tokens (e.g. reference numbers, years, and other digit sequences) in the text.

    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
     Tecn
    -0.94
     menar
    -0.88
     тук
    -0.88
    どうしても
    -0.87
    ələ
    -0.87
     Singapur
    -0.86
     on
    -0.85
    🏭
    -0.85
     truk
    -0.85
    illy
    -0.85
    POSITIVE LOGITS
     celé
    1.04
     două
    0.95
     somebody
    0.89
     و
    0.83
    licans
    0.82
    abstractmethod
    0.81
    ensä
    0.81
     konkrét
    0.80
     เรา
    0.80
     ehemaligen
    0.80
    Activations Density 0.089%

    No Known Activations