© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7051
    Prev
    Next
    INDEX
    Explanations

    belonging to someone or something

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

    belonging to categories

    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
    に向
    0.46
    كيف
    0.40
     использованием
    0.40
     działania
    0.40
     разнообраз
    0.39
     ايجاد
    0.39
    鏢
    0.39
    Existing
    0.39
    に対し
    0.39
    ૪
    0.38
    POSITIVE LOGITS
     belonged
    1.10
     belong
    1.09
     belongs
    1.09
    属于
    1.04
     Belong
    0.97
    belongs
    0.95
    belong
    0.92
     pertence
    0.91
     принадлежит
    0.88
     thuộc
    0.87
    Activations Density 0.014%

    No Known Activations