© 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. 112632
    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
     ‘’
    -1.64
     étrangère
    -1.61
     canadienne
    -1.50
    Its
    -1.48
     grecque
    -1.48
     ambayo
    -1.43
     ۲
    -1.43
    檠
    -1.42
     STILL
    -1.41
     japonaise
    -1.41
    POSITIVE LOGITS
    erdings
    1.45
    ).
    1.41
     naviguant
    1.33
     those
    1.30
    と呼ば
    1.25
     infeksi
    1.25
     consideran
    1.23
    作り方
    1.23
    ⓪
    1.22
     applicable
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.