© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77610
    Prev
    Next
    INDEX
    Explanations

    to see or understand

    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
    explain
    -1.22
     doman
    -0.99
     ($('#
    -0.98
    
    -0.96
    Prove
    -0.96
    叆
    -0.95
     blz
    -0.95
     alho
    -0.94
     لتح
    -0.93
    izzazione
    -0.92
    POSITIVE LOGITS
     see
    2.75
     gauge
    2.56
     get
    2.41
     assess
    1.92
     gau
    1.89
     understand
    1.80
     better
    1.74
    gauge
    1.70
     judge
    1.66
    see
    1.62
    Activations Density 0.056%

    No Known Activations