© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59789
    Prev
    Next
    INDEX
    Explanations

    what happens or indicates

    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
    atalos
    -1.42
     new
    -1.28
     darbu
    -1.24
     İl
    -1.23
    {~
    -1.23
    HASAN
    -1.21
     some
    -1.19
    sữa
    -1.16
    ALWAYS
    -1.13
     pagrind
    -1.12
    POSITIVE LOGITS
     a
    1.54
    cześ
    1.46
     $-$
    1.43
    ">'
    1.42
    routeProvider
    1.41
    ↵
    1.39
     –
    1.32
    嘞
    1.32
     タン
    1.32
    )$}
    1.28
    Activations Density 0.109%

    No Known Activations