© 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. 73988
    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
     and
    -1.40
     bebidas
    -1.10
     camisetas
    -1.07
     esses
    -1.07
     serpiente
    -1.05
     limón
    -1.05
     لأنه
    -1.04
    -1.04
     avantage
    -1.03
     infecciones
    -1.03
    POSITIVE LOGITS
     are
    2.14
     were
    1.70
     have
    1.30
     archivio
    1.06
     would
    1.06
     together
    1.06
     surrounding
    1.05
     coexist
    1.05
     can
    1.02
     will
    1.02
    Activations Density 0.076%

    No Known Activations