© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103694
    Prev
    Next
    INDEX
    Explanations

    Seattle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tempting
    -2.45
    来源于
    -2.27
     разом
    -2.25
     stuffy
    -2.22
     וה
    -2.20
     deleterious
    -2.17
     邊
    -2.13
     хто
    -2.13
    AutoresizingMask
    -2.06
     xuyên
    -2.02
    POSITIVE LOGITS
    ка
    3.00
    岖
    2.34
    ՚
    2.25
    )
    2.23
    打量
    2.13
     reaffirm
    2.13
    issait
    2.11
    >}
    2.11
    ENCIÓN
    2.11
    定休日
    2.09
    Activations Density 0.003%

    No Known Activations