© 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. 10-GEMMASCOPE-RES-131K
    7. 66714
    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
     It
    -1.33
     bunun
    -1.23
    which
    -1.17
     几
    -1.16
    ↵
    -1.16
    同样
    -1.10
    elde
    -1.09
    who
    -1.09
     mehrere
    -1.08
     was
    -1.05
    POSITIVE LOGITS
     atlik
    1.36
     deportivas
    1.31
     {
    1.26
    ruguay
    1.26
    嫚
    1.24
    graffiti
    1.23
    XICO
    1.23
     esthétique
    1.21
    dailymail
    1.21
    [:,:,
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.