© 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-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 104436
    Prev
    Next
    INDEX
    Explanations

    AI in games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    僳
    0.59
     அறிவியல்
    0.58
     விஞ்ஞான
    0.57
    ,
    0.54
    碑
    0.54
     entorno
    0.53
    <bos>
    0.53
    科研
    0.53
    vival
    0.52
     иннова
    0.52
    POSITIVE LOGITS
    0
    0.70
    ਮ
    0.62
    기
    0.56
    ри
    0.53
    ра
    0.53
    RAF
    0.52
    의
    0.51
     Rivera
    0.50
     জাহ
    0.49
     ফ্লাইট
    0.48
    Activations Density 0.031%

    No Known Activations