© 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. 22-GEMMASCOPE-RES-131K
    7. 65624
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     all
    -1.18
     critics
    -0.93
     and
    -0.90
    專業
    -0.90
     Souver
    -0.89
    spě
    -0.88
     sué
    -0.88
     larger
    -0.88
     suisse
    -0.88
     convento
    -0.88
    POSITIVE LOGITS
     réessayer
    1.11
     réun
    1.10
    ith
    1.05
    Desen
    1.05
     traditionnels
    1.05
    bulaire
    1.01
     acepción
    0.99
    踅
    0.98
    chläge
    0.97
    ⟢
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.