© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35797
    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
     its
    -1.56
     desfile
    -1.30
    uruh
    -1.19
    前言
    -1.16
    ATUM
    -1.13
     alerg
    -1.10
    dillera
    -1.09
     usadas
    -1.09
    ICIÓN
    -1.06
     diterapkan
    -1.05
    POSITIVE LOGITS
    carus
    1.11
    opie
    1.10
    is
    1.06
    ”
    1.05
    ,
    1.05
    ß
    1.05
    –
    1.04
    k
    1.03
     ue
    1.02
     getY
    1.02
    Activations Density 0.000%

    No Known Activations