© 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. 12459
    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
     so
    -1.34
    levis
    -1.33
     then
    -1.26
     sowas
    -1.25
     it
    -1.25
     such
    -1.20
     similar
    -1.18
    kimono
    -1.18
     subsequently
    -1.17
     few
    -1.16
    POSITIVE LOGITS
     signifikan
    1.36
    Fernsehserie
    1.32
    ор
    1.25
     risiko
    1.20
    й
    1.18
    recyclerview
    1.18
    шего
    1.18
    ৭
    1.16
    tifiable
    1.16
     для
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.