© 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. 39318
    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
    -1.99
     most
    -1.96
     sizable
    -1.80
     unique
    -1.76
     terrible
    -1.74
     enviado
    -1.73
     nifty
    -1.73
     every
    -1.73
     this
    -1.73
     tangible
    -1.73
    POSITIVE LOGITS
    ebly
    1.92
     estabelec
    1.83
    鶿
    1.76
    沵
    1.71
    ʹ
    1.68
     canadian
    1.66
     recentemente
    1.63
     Dinas
    1.60
    ’
    1.60
    ate
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.