© 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. 68645
    Prev
    Next
    INDEX
    Explanations

    numbered military units

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

    The neuron activates on ordinal numbers (1st, 2nd, 3rd, etc.) when they’re part of military unit or formation names.

    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
     exportaciones
    -1.18
     jendela
    -1.17
    zeß
    -1.12
     time
    -1.11
     продукта
    -1.11
    なるべく
    -1.09
     Betrag
    -1.09
    Q
    -1.07
     new
    -1.06
    enging
    -1.06
    POSITIVE LOGITS
     of
    1.49
     AssemblyCulture
    1.40
     famili
    1.29
     бампер
    1.23
    ølge
    1.23
    ának
    1.18
    班级
    1.15
    ִּ
    1.10
    drawSprites
    1.10
    MILLISECONDS
    1.09
    Activations Density 0.065%

    No Known Activations