© 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. 9426
    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
    T
    -1.26
     is
    -1.21
    N
    -1.17
     also
    -1.15
     Since
    -1.13
     first
    -1.12
    E
    -1.12
     In
    -1.12
     IN
    -1.11
     your
    -1.10
    POSITIVE LOGITS
     faſt
    1.34
     FOTO
    1.27
     plafon
    1.26
     évé
    1.26
     relata
    1.24
     rése
    1.23
     éven
    1.23
    chsel
    1.23
     imprim
    1.22
     PROBLE
    1.21
    Activations Density 0.000%

    No Known Activations