© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5714
    Prev
    Next
    INDEX
    Explanations

    text summarization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     spezif
    1.43
    娆
    1.35
    اا
    1.30
     Polaribacter
    1.29
    pairing
    1.28
    色素
    1.25
     ভাগ্যবান
    1.24
    zal
    1.23
    选择
    1.23
    तरह
    1.22
    POSITIVE LOGITS
     summarizing
    1.43
    훑
    1.38
     summaries
    1.37
     summarizes
    1.37
     '\\;'
    1.28
     overview
    1.25
    摘要
    1.23
     summarize
    1.21
     summar
    1.20
     summary
    1.20
    Activations Density 0.258%

    No Known Activations