© 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. 11087
    Prev
    Next
    INDEX
    Explanations

    code blocks relating to `try` or function definition

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     trending
    -0.92
     کیلو
    -0.90
     klima
    -0.90
    kere
    -0.84
    bier
    -0.83
     alcalde
    -0.82
     мастеров
    -0.82
     kata
    -0.81
     campeones
    -0.81
    logged
    -0.81
    POSITIVE LOGITS
     samoz
    1.07
    try
    0.97
     podrá
    0.91
    ācija
    0.86
     Monday
    0.85
    ulco
    0.84
    ónia
    0.84
     keduanya
    0.81
     ability
    0.81
     try
    0.81
    Activations Density 0.004%

    No Known Activations