© 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. 27926
    Prev
    Next
    INDEX
    Explanations

    legal citation numbers

    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
     like
    -0.88
    Externí
    -0.88
    therapist
    -0.83
     sesu
    -0.83
     seny
    -0.82
     idiota
    -0.82
    mailed
    -0.81
     diras
    -0.81
     already
    -0.80
    gráficas
    -0.80
    POSITIVE LOGITS
     اخیر
    0.87
     cases
    0.86
     mitig
    0.86
     resort
    0.85
     Ces
    0.82
     ostat
    0.79
     conduite
    0.79
    大陆
    0.79
     shield
    0.79
     获取
    0.79
    Activations Density 0.024%

    No Known Activations