© 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. 34-GEMMASCOPE-RES-131K
    7. 60586
    Prev
    Next
    INDEX
    Explanations

    Share on

    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_34/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
    ülle
    -0.77
     skla
    -0.75
     descub
    -0.74
     fumig
    -0.73
    cipline
    -0.72
     nje
    -0.71
    cerer
    -0.71
    印
    -0.71
    locks
    -0.71
     rebo
    -0.70
    POSITIVE LOGITS
     try
    0.87
     prø
    0.85
     Try
    0.80
     tried
    0.78
    wait
    0.77
    try
    0.77
    Tried
    0.75
     Tried
    0.75
     Habitats
    0.74
     mobs
    0.73
    Activations Density 0.013%

    No Known Activations