© 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. 110831
    Prev
    Next
    INDEX
    Explanations

    rolling papers

    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
     Reiter
    -0.77
     resourceCulture
    -0.72
    Kad
    -0.71
     съм
    -0.70
    лек
    -0.70
     Adoption
    -0.70
     enfants
    -0.69
    Koordin
    -0.68
     Vries
    -0.68
     Eliot
    -0.68
    POSITIVE LOGITS
     rolling
    1.56
     papers
    1.52
    rolling
    1.41
     Rolling
    1.37
     Papers
    1.28
    Rolling
    1.25
     paper
    1.23
    Papers
    1.07
    paper
    1.07
    papers
    1.06
    Activations Density 0.012%

    No Known Activations