© 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. 25952
    Prev
    Next
    INDEX
    Explanations

    knew

    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
     hivyo
    -0.78
     Jans
    -0.77
    nvarchar
    -0.74
    imageUrl
    -0.74
    vård
    -0.73
     silang
    -0.73
    ÑO
    -0.72
     hanggang
    -0.71
    小时
    -0.71
     Mantis
    -0.70
    POSITIVE LOGITS
     knew
    6.53
    knew
    4.16
     Knew
    3.48
     знал
    3.47
     знали
    3.19
     known
    2.86
     knowing
    2.53
     sabía
    2.53
     sabia
    2.38
     wusste
    2.33
    Activations Density 0.071%

    No Known Activations