© 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. 60660
    Prev
    Next
    INDEX
    Explanations

    Royal institutions

    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
    ibra
    -0.96
     olabilir
    -0.85
     télécharge
    -0.80
    MEAN
    -0.79
     スポーツ
    -0.79
     rzeczyw
    -0.79
    ardless
    -0.77
     whiche
    -0.76
     國
    -0.75
    actéris
    -0.75
    POSITIVE LOGITS
     Holloway
    0.98
     Blind
    0.89
     Academy
    0.87
     Society
    0.81
     Navy
    0.80
     College
    0.79
     Belgian
    0.78
     Ginger
    0.76
     Signals
    0.75
     Antwerp
    0.75
    Activations Density 0.013%

    No Known Activations