© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124180
    Prev
    Next
    INDEX
    Explanations

    car specifications and models

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

    usage

    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_31_width_262k_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
     সৌন্দর
    0.47
    瑰
    0.46
    一方面
    0.43
    сад
    0.43
    人々
    0.43
    学校
    0.42
     मिलीमीटर
    0.42
    го
    0.42
    人类
    0.42
    贵
    0.42
    POSITIVE LOGITS
     Smy
    0.50
     gebruiken
    0.50
     اسماع
    0.50
     nemen
    0.48
     استخدم
    0.48
     Sinal
    0.47
     potom
    0.46
     مين
    0.46
     يسم
    0.46
     reis
    0.46
    Activations Density 0.000%

    No Known Activations