© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14003
    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
     again
    -1.30
     couverts
    -1.02
     couver
    -0.97
    iramente
    -0.94
    arschijnlijk
    -0.93
     klein
    -0.93
    нительно
    -0.92
    rall
    -0.92
     maquina
    -0.91
    GRAFIA
    -0.90
    POSITIVE LOGITS
     parfois
    0.96
    ône
    0.90
     иногда
    0.89
     народу
    0.88
     contributo
    0.87
     spesso
    0.87
    有时
    0.87
     heuti
    0.84
    有时候
    0.83
     entiende
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.