© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91555
    Prev
    Next
    INDEX
    Explanations

    groupId and artifactId in XML

    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
     globalization
    -1.26
     gasket
    -1.21
     groundwater
    -1.16
     grassland
    -1.16
     Gandhi
    -1.13
     grammar
    -1.08
     graphics
    -1.05
     glucose
    -1.04
     girlfriend
    -1.03
     GraphQL
    -1.03
    POSITIVE LOGITS
     nong
    1.92
     Nong
    0.98
     cDNA
    0.84
     pineapple
    0.79
    emlrt
    0.77
    떨
    0.77
    𝐠
    0.77
     Hessian
    0.75
     cbd
    0.75
    اظ
    0.74
    Activations Density 0.213%

    No Known Activations