© 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. 15002
    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
     by
    -1.92
     before
    -1.75
     as
    -1.73
     one
    -1.58
     because
    -1.47
    😈
    -1.41
    榈
    -1.38
    🤠
    -1.38
    🥶
    -1.36
    (/^
    -1.34
    POSITIVE LOGITS
     нужен
    1.39
    <bos>
    1.38
     ſaid
    1.37
     maniere
    1.36
    你也
    1.36
    )-
    1.36
     esperan
    1.34
     quieren
    1.34
     are
    1.32
    .’
    1.32
    Activations Density 0.007%

    No Known Activations