© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11645
    Prev
    Next
    INDEX
    Explanations

    concepts and experiences

    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
    芣
    -1.41
     perioden
    -1.24
    手段
    -1.23
    BY
    -1.23
    GIA
    -1.22
     incu
    -1.22
    밖
    -1.22
    ."
    -1.21
    щата
    -1.21
     archite
    -1.17
    POSITIVE LOGITS
     that
    1.50
     be
    1.42
     from
    1.41
    кость
    1.32
    那时
    1.20
     pensó
    1.18
    getS
    1.16
    ølge
    1.15
     bernama
    1.12
     debilidad
    1.12
    Activations Density 0.176%

    No Known Activations