© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31126
    Prev
    Next
    INDEX
    Explanations

    opening parentheses and brackets

    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
     réglementation
    -0.90
    我觉得
    -0.88
    你在
    -0.87
     furthermore
    -0.87
    之间
    -0.86
    已經
    -0.86
    できない
    -0.84
     undoubtedly
    -0.82
    その他
    -0.81
     him
    -0.80
    POSITIVE LOGITS
    zucht
    0.88
    tehende
    0.88
     exceptionnelle
    0.88
    forChild
    0.88
     spezi
    0.88
    Sebagai
    0.87
    enthal
    0.87
     famed
    0.87
     souvent
    0.85
    
    0.85
    Activations Density 0.002%

    No Known Activations