© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60511
    Prev
    Next
    INDEX
    Explanations

    game event

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

    This neuron detects the word “game” (including hyphenated and title‐case occurrences) in 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_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
    媪
    -2.11
    趼
    -2.09
    )....
    -2.02
     '
    -2.02
    俢
    -1.78
    甗
    -1.78
    𐐀
    -1.77
    ).....
    -1.76
    睺
    -1.73
    珽
    -1.73
    POSITIVE LOGITS
    ↵↵
    2.66
    >
    2.02
     But
    1.98
    :
    1.84
    vestres
    1.82
    ቧ
    1.78
     einem
    1.72
    According
    1.70
     folgende
    1.70
     stabil
    1.67
    Activations Density 0.041%

    No Known Activations