© 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. 10-GEMMASCOPE-RES-131K
    7. 21965
    Prev
    Next
    INDEX
    Explanations

    game and sound

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

    The neuron strongly responds whenever the document mentions the word “game.”

    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
     with
    -1.80
     truly
    -1.59
     this
    -1.49
     two
    -1.48
    vaných
    -1.45
     three
    -1.45
     tilbud
    -1.38
     tilgjenge
    -1.34
     increased
    -1.32
     from
    -1.30
    POSITIVE LOGITS
     Atención
    1.53
    蓠
    1.52
     visto
    1.48
    一部
    1.44
    нс
    1.41
    ☫
    1.40
    MINE
    1.38
    ategy
    1.34
     eer
    1.33
    hancers
    1.32
    Activations Density 0.024%

    No Known Activations