© 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. 69097
    Prev
    Next
    INDEX
    Explanations

    Steam, Valve, or VR interfaces

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

    The neuron is triggered by mentions of Valve’s Steam platform (e.g. “Valve,” “Steam,” related Steam-API or Steam overlay 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_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
     voitures
    -1.37
     vitesses
    -1.35
    鹚
    -1.32
     same
    -1.28
     MAUR
    -1.27
     ralph
    -1.27
     MICHAEL
    -1.26
     Vnd
    -1.23
     Uniwers
    -1.23
     無地
    -1.23
    POSITIVE LOGITS
     you
    1.73
     h
    1.57
     cocin
    1.47
     C
    1.43
                        
    1.42
     murky
    1.41
     M
    1.39
            
    1.38
     P
    1.37
                 
    1.36
    Activations Density 0.031%

    No Known Activations