© 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. 36692
    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
    Surprisingly
    -1.07
     demonstrates
    -1.04
     epitom
    -1.02
     artful
    -0.98
     investigations
    -0.98
    amling
    -0.98
     Surprisingly
    -0.95
    Interestingly
    -0.94
    Many
    -0.94
    ९
    -0.94
    POSITIVE LOGITS
    褙
    1.23
     aerolí
    1.18
     fermer
    1.17
    ︲
    1.16
    幛
    1.13
    揹
    1.13
     devenir
    1.09
    凩
    1.09
    ≻
    1.09
     hombros
    1.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.