© 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. 10-GEMMASCOPE-RES-131K
    7. 59350
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    …»
    -1.57
    ”-
    -1.55
    ……”
    -1.48
    {
    -1.47
    eckt
    -1.42
     コラボ
    -1.41
    PreExecute
    -1.38
    pkins
    -1.36
    </strong>
    -1.33
     necessary
    -1.33
    POSITIVE LOGITS
    琹
    1.47
     they
    1.45
     maît
    1.43
    Postup
    1.40
     ciddi
    1.36
     测试
    1.35
     harika
    1.34
     mutfak
    1.34
    érales
    1.33
     بت
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.