© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92360
    Prev
    Next
    INDEX
    Explanations

    Battlefield video games

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

    The neuron activates on numeric expressions—especially prominent digits or multi‐digit numbers like counts, measurements, or version identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Propulsion
    -0.75
    🏯
    -0.75
    tový
    -0.72
    綜合報導
    -0.72
    أة
    -0.72
     spar
    -0.72
     віта
    -0.72
     Martian
    -0.71
    opencv
    -0.71
    önt
    -0.71
    POSITIVE LOGITS
     Battlefield
    1.15
     DICE
    1.15
     BF
    1.11
    BF
    1.03
    Battlefield
    1.02
    bf
    0.85
    Bf
    0.82
     Bad
    0.78
     CTE
    0.76
     Combined
    0.75
    Activations Density 0.008%

    No Known Activations