© 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. 12243
    Prev
    Next
    INDEX
    Explanations

    multiple choice questions

    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
     Rowling
    -0.80
    ән
    -0.73
     Pollack
    -0.72
     sonder
    -0.71
    ;',
    -0.71
    泾
    -0.70
    recur
    -0.69
    鼾
    -0.68
     kamp
    -0.67
     Sonny
    -0.67
    POSITIVE LOGITS
     multiple
    3.67
     Multiple
    3.59
    Multiple
    3.58
    multiple
    3.22
    MULTIPLE
    2.63
     MULTIPLE
    2.52
     múltiples
    2.23
     MCQ
    2.16
     multiples
    2.03
     múl
    1.88
    Activations Density 0.057%

    No Known Activations