© 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. 110816
    Prev
    Next
    INDEX
    Explanations

    natural vs artificial

    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
     prototyping
    -0.79
     nonverbal
    -0.75
    [*
    -0.73
    왑
    -0.73
     legiti
    -0.72
    oara
    -0.72
    SEX
    -0.72
    Дереккөздер
    -0.70
    enez
    -0.70
    iausi
    -0.70
    POSITIVE LOGITS
     artificial
    5.19
    artificial
    4.41
     artificially
    4.13
    Artificial
    4.00
     Artificial
    3.84
     искус
    3.70
     künst
    3.53
    人工
    3.45
     artificiales
    3.28
     unnatural
    3.23
    Activations Density 0.247%

    No Known Activations