© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110973
    Prev
    Next
    INDEX
    Explanations

    take place, take part, take note

    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
     Inf
    -0.83
     Invisible
    -0.83
     Observer
    -0.79
    fords
    -0.76
     Alemanha
    -0.76
     Luigi
    -0.75
     Hansen
    -0.75
     Ion
    -0.74
     Kriegs
    -0.74
     Oracle
    -0.73
    POSITIVE LOGITS
     away
    1.14
     advantage
    1.01
     estric
    0.96
     wichtigen
    0.85
     turns
    0.85
     off
    0.85
     risks
    0.82
     desempeño
    0.81
     precautions
    0.81
    UTIVE
    0.80
    Activations Density 0.008%

    No Known Activations