© 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. 22-GEMMASCOPE-RES-131K
    7. 72951
    Prev
    Next
    INDEX
    Explanations

    C# set; construct and distinct topics

    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_22/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
     either
    -1.23
    ینده
    -1.09
     itself
    -1.08
     retten
    -1.05
     Lokales
    -1.02
    IConfiguration
    -0.99
     ideen
    -0.99
    戋
    -0.98
    either
    -0.98
    BufferException
    -0.97
    POSITIVE LOGITS
    ஔ
    1.17
     Rov
    1.09
     vanske
    1.09
    excellents
    1.07
     internazionali
    1.06
     dårlig
    1.05
    潜力
    1.04
     chaussures
    1.04
    些
    1.03
     šte
    1.02
    Activations Density 0.002%

    No Known Activations