© 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. 47595
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bedeckt
    -1.00
     Dwar
    -0.81
    普通的
    -0.79
    óloga
    -0.79
    roskop
    -0.78
     الاجتماعي
    -0.76
     Làm
    -0.75
     Increment
    -0.75
    稍微
    -0.75
     increment
    -0.72
    POSITIVE LOGITS
     okresie
    0.90
    жд
    0.90
    iosync
    0.86
     czasie
    0.86
    replication
    0.84
     formie
    0.80
    runnable
    0.79
    financial
    0.78
     ananas
    0.77
     grec
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.