© 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. 84519
    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
     because
    -2.25
     their
    -2.23
     using
    -2.11
     longstanding
    -2.03
     only
    -1.96
     tailored
    -1.95
     with
    -1.94
     both
    -1.93
     several
    -1.93
     taking
    -1.92
    POSITIVE LOGITS
     quintessential
    2.34
     momentous
    2.23
     captivating
    2.11
     gigantic
    2.06
     luscious
    2.03
     REALLY
    2.02
     pivotal
    2.00
     amazingly
    1.98
     blatant
    1.97
     magnificent
    1.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.