© 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. 9436
    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
     you
    -1.51
     malay
    -0.98
    CharStream
    -0.96
     scoperta
    -0.94
     大学
    -0.94
    mpo
    -0.91
     bae
    -0.90
     chiedere
    -0.90
     eerst
    -0.90
    然后
    -0.89
    POSITIVE LOGITS
     bonitas
    1.07
     impeccable
    1.00
     has
    1.00
     delicious
    0.99
     heartfelt
    0.99
     joten
    0.98
     heartily
    0.95
    Indexes
    0.94
     enormous
    0.94
     hardworking
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.