© 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. 34-GEMMASCOPE-RES-131K
    7. 55706
    Prev
    Next
    INDEX
    Explanations

    CrossPlatformInput related to Unity

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

    The neuron is triggered by standalone numeric tokens (numbers or version/file ID values) in code or data.

    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
     Komun
    -0.87
    HUN
    -0.87
     ilustrasi
    -0.87
     opérateur
    -0.86
    gendes
    -0.86
    Kontakt
    -0.85
     diskusi
    -0.83
    Biografía
    -0.82
    𝘵
    -0.81
     Î
    -0.80
    POSITIVE LOGITS
     Health
    1.05
     GameManager
    1.00
    GameManager
    1.00
     game
    1.00
     camera
    0.98
     GM
    0.98
     Manager
    0.97
     save
    0.97
     manager
    0.96
     Camera
    0.95
    Activations Density 0.012%

    No Known Activations