Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 139
    Prev
    Next
    INDEX
    Explanations

    site or place

    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_16_width_16k_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
     सीनियर
    0.55
    nearest
    0.52
    nyc
    0.52
    头部
    0.51
     полости
    0.50
    咛
    0.50
    ಮ
    0.50
    ómicas
    0.49
     ngờ
    0.48
     муниципа
    0.48
    POSITIVE LOGITS
     
    0.59
    us
    0.53
     It
    0.53
    ف
    0.51
     webs
    0.50
     eben
    0.50
     ober
    0.50
     ISP
    0.50
     situs
    0.49
     dom
    0.48
    Activations Density 0.000%

    No Known Activations