© 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. 73433
    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
     offenbar
    -1.10
     ursprünglich
    -1.09
     manchmal
    -1.08
    Merkmale
    -1.06
     plötzlich
    -1.06
     offiziell
    -1.02
     vermutlich
    -1.02
     ilumin
    -1.00
     bekämp
    -0.98
    八年
    -0.96
    POSITIVE LOGITS
     réaliser
    1.03
     devrez
    1.00
    はある
    0.95
     jj
    0.94
     also
    0.92
    kara
    0.91
    会不会
    0.90
     générer
    0.90
    却是
    0.90
    WEBPACK
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.