© 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. 358
    Prev
    Next
    INDEX
    Explanations

    news reporting outlets

    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
     coer
    -0.86
     NHK
    -0.84
    icação
    -0.80
    古い
    -0.77
    ressional
    -0.76
     limp
    -0.76
     dậy
    -0.74
    烟
    -0.71
     disting
    -0.71
    межу
    -0.71
    POSITIVE LOGITS
     Examiner
    1.32
     Huffington
    1.24
    Huff
    1.19
    嬷
    1.07
     examiner
    1.04
    Exam
    1.03
     Fox
    1.00
     AOL
    0.99
     Huff
    0.96
    huff
    0.94
    Activations Density 0.122%

    No Known Activations