© 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. 34-GEMMASCOPE-RES-131K
    7. 116072
    Prev
    Next
    INDEX
    Explanations

    organization name followed by of

    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_34/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
     something
    -1.19
     estrema
    -1.13
     verdaderas
    -1.10
     gekauft
    -1.05
     either
    -1.01
     allarg
    -0.99
     proprietario
    -0.97
     extremely
    -0.95
     чувства
    -0.95
     meaning
    -0.94
    POSITIVE LOGITS
     of
    3.17
    ของ
    2.14
     at
    1.77
     của
    1.72
     thuộc
    1.52
     של
    1.48
     της
    1.40
     within
    1.40
     part
    1.28
     часть
    1.27
    Activations Density 0.108%

    No Known Activations