© 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. 12982
    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
     their
    -1.09
     from
    -1.02
     for
    -0.97
     glede
    -0.96
     its
    -0.93
    tidos
    -0.93
     has
    -0.90
    引言
    -0.88
     on
    -0.88
     without
    -0.88
    POSITIVE LOGITS
    VERY
    1.10
     continuará
    1.10
     volverá
    1.05
     competencias
    1.05
     hacerlo
    1.01
    pecified
    1.00
    wasn
    1.00
     essence
    0.99
    banez
    0.99
     novedades
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.