© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4060
    Prev
    Next
    INDEX
    Explanations

    html element attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Paragraph
    1.83
    cuts
    1.61
    Blogs
    1.59
     Editor
    1.50
     Blogs
    1.50
    Books
    1.49
    绉
    1.48
     κύ
    1.48
    Paragraph
    1.47
     kirjo
    1.46
    POSITIVE LOGITS
    hesus
    1.42
    methylsulfanyl
    1.28
    sulfanyl
    1.24
    indler
    1.23
     Gentile
    1.22
     crossorigin
    1.20
     tamper
    1.18
    elace
    1.18
    }}(-
    1.17
     keepers
    1.14
    Activations Density 0.003%

    No Known Activations