© 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. 72796
    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
    -1.57
     from
    -1.57
     for
    -1.48
     at
    -1.29
     has
    -1.24
     epitom
    -1.22
     first
    -1.20
     helps
    -1.19
     many
    -1.19
     they
    -1.19
    POSITIVE LOGITS
    訁
    1.23
     🥰
    1.23
    Ingredienti
    1.21
     💕
    1.13
     establecidos
    1.12
     ™
    1.10
    Locatie
    1.10
    Prijs
    1.09
     almacenar
    1.09
     😁
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.