© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    open [determiner] [noun]

    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
    _
    -1.90
    </h2>
    -1.66
     bizony
    -1.50
     animado
    -1.49
     некоторы
    -1.47
     coloque
    -1.42
     rús
    -1.42
    应该
    -1.41
     vannak
    -1.41
    螄
    -1.40
    POSITIVE LOGITS
    ㆆ
    1.63
    紧接着
    1.57
    是这样
    1.54
     производстве
    1.54
    给我们
    1.53
    屜
    1.52
    ucho
    1.52
     Läs
    1.48
     smacked
    1.48
    月的
    1.47
    Activations Density 0.017%

    No Known Activations