© 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. 115473
    Prev
    Next
    INDEX
    Explanations

    codes and programming comments

    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
    苦手
    -0.91
     לפי
    -0.89
    Výhody
    -0.84
     przewod
    -0.82
     notwithstanding
    -0.81
     numberOf
    -0.79
     meravigli
    -0.79
    
    -0.78
     than
    -0.77
    Ɠ
    -0.77
    POSITIVE LOGITS
     NI
    1.01
     NST
    1.00
     NU
    0.98
     N
    0.98
     NSS
    0.94
     ND
    0.90
    NU
    0.88
     NS
    0.87
     NIS
    0.86
    reorder
    0.86
    Activations Density 1.561%

    No Known Activations