© 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. 112446
    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
    ⚋
    -3.08
     ersten
    -3.03
    媄
    -2.70
    </h3>
    -2.64
     rufen
    -2.58
     With
    -2.56
    куда
    -2.52
     This
    -2.50
     thwart
    -2.45
     inesper
    -2.44
    POSITIVE LOGITS
    읭
    3.02
    鱨
    2.69
    >
    2.69
     verſ
    2.63
    赑
    2.61
    鬭
    2.61
    sandalia
    2.61
    {
    2.59
     itſelf
    2.59
     dieß
    2.59
    Activations Density 0.000%

    No Known Activations