© 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. 71627
    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
     which
    -1.10
    paru
    -0.99
     sufficiently
    -0.96
     including
    -0.96
    endus
    -0.95
     who
    -0.94
    fleur
    -0.94
     electrónico
    -0.93
    UserContext
    -0.92
     Spanyol
    -0.92
    POSITIVE LOGITS
    都係
    1.08
     ahora
    1.02
     überhaupt
    1.02
    benhavn
    1.02
    笅
    1.00
     множество
    0.99
    샅
    0.99
    Actividad
    0.99
    ôles
    0.98
     machte
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.