© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128426
    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
    -2.31
     all
    -1.97
     both
    -1.94
     or
    -1.93
     by
    -1.83
     first
    -1.82
     five
    -1.79
     only
    -1.78
     more
    -1.77
     two
    -1.76
    POSITIVE LOGITS
     geene
    1.58
    Informazioni
    1.56
     fenô
    1.49
    Ingredienti
    1.48
    Dettagli
    1.46
     также
    1.45
    Preparazione
    1.43
     poë
    1.42
     Эти
    1.42
     faciliter
    1.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.