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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14667
    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
     in
    -0.98
     having
    -0.97
     by
    -0.95
     menekan
    -0.92
     esferas
    -0.91
    usstsein
    -0.88
     at
    -0.88
     like
    -0.88
     postup
    -0.87
     według
    -0.86
    POSITIVE LOGITS
     SAME
    1.12
     tamaños
    0.99
    SAME
    0.98
     lustig
    0.96
     idem
    0.96
     disney
    0.93
    ﻷ
    0.93
     praticamente
    0.93
     senderos
    0.93
    ➑
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.