© 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. 31-GEMMASCOPE-2-RES-262K
    4. 126231
    Prev
    Next
    INDEX
    Explanations

    Apple product details and ecosystem

    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_31_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
    大
    0.64
    準
    0.48
    京
    0.47
    
    0.47
    人
    0.46
    ER
    0.46
     audition
    0.46
    ن
    0.45
    中
    0.45
    YA
    0.44
    POSITIVE LOGITS
    ponen
    0.58
    ostiene
    0.46
    atuur
    0.46
     प्रभावी
    0.46
     विनियमन
    0.45
     реализу
    0.44
     manca
    0.44
    парат
    0.44
     pérdidas
    0.43
     semua
    0.43
    Activations Density 0.001%

    No Known Activations