© 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. 216
    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
     to
    -1.30
     begin
    -1.18
     using
    -1.18
     just
    -1.16
     when
    -1.12
     get
    -1.11
     what
    -1.09
     relating
    -1.09
     most
    -1.08
     procedures
    -1.08
    POSITIVE LOGITS
    THEY
    1.08
    BeginContext
    1.08
    ENDIX
    1.02
     filtros
    1.02
     momentous
    1.00
    铊
    1.00
    exemple
    0.99
     weinig
    0.96
    Noch
    0.96
    vande
    0.94
    Activations Density 0.000%

    No Known Activations