© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3266
    Prev
    Next
    INDEX
    Explanations

    game object components and properties

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

    unity game development concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arote
    0.50
    aporte
    0.47
    testng
    0.45
     事業
    0.45
     JOSE
    0.45
    affirm
    0.45
    pageno
    0.45
    羥
    0.45
    afood
    0.44
    getRequest
    0.44
    POSITIVE LOGITS
    GameObject
    1.81
     GameObject
    1.77
     UnityEngine
    1.66
    UnityEngine
    1.63
    Rigidbody
    1.59
     prefab
    1.59
    Prefab
    1.57
     gameObject
    1.49
     Mathf
    1.48
    prefab
    1.48
    Activations Density 0.021%

    No Known Activations