© 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. 22-GEMMASCOPE-RES-131K
    7. 27555
    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
     if
    -1.30
     that
    -1.19
     nine
    -1.09
     sebelum
    -1.06
     what
    -1.05
     first
    -1.03
     before
    -1.03
     eight
    -1.02
     procedures
    -1.02
     mindig
    -1.02
    POSITIVE LOGITS
     militari
    0.99
     tril
    0.93
     mening
    0.91
     scintill
    0.91
     Dinas
    0.91
     impati
    0.89
     knap
    0.89
     ombro
    0.89
     psychiat
    0.88
     trag
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.