© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48483
    Prev
    Next
    INDEX
    Explanations

    .NET Framework namespaces

    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
     مثل
    -0.83
     雑誌
    -0.76
     cometh
    -0.75
    ільки
    -0.72
     Lepidoptera
    -0.71
     indef
    -0.69
    ورد
    -0.69
     într
    -0.68
    entiel
    -0.68
    cives
    -0.68
    POSITIVE LOGITS
     web
    1.14
    web
    1.06
    Web
    0.96
     Web
    0.91
     motocic
    0.89
     Corazón
    0.84
     ഗ
    0.82
     text
    0.81
     ">=
    0.80
     immobilier
    0.79
    Activations Density 0.022%

    No Known Activations