© 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. 35022
    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
    adaran
    -1.03
     Ministers
    -1.00
    ј
    -0.99
    ͔
    -0.99
     wenig
    -0.99
    íguez
    -0.99
    niego
    -0.98
     aasta
    -0.97
    tidig
    -0.96
    RTLR
    -0.96
    POSITIVE LOGITS
    purchased
    1.13
     textu
    1.02
    dessin
    1.01
    でしょうね
    0.94
     videa
    0.94
    Région
    0.94
    お話
    0.92
    Clic
    0.92
    Zon
    0.92
    んじゃ
    0.89
    Activations Density 0.000%

    No Known Activations