© 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. 34499
    Prev
    Next
    INDEX
    Explanations

    using System

    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
     operar
    -0.84
    isNameExpr
    -0.78
     fendi
    -0.78
    ómicos
    -0.78
    Probab
    -0.77
     дав
    -0.77
    影视
    -0.76
    čno
    -0.76
    Synonymes
    -0.74
    长得
    -0.73
    POSITIVE LOGITS
    disposing
    1.20
    werd
    0.98
     אם
    0.98
     true
    0.91
    Occurs
    0.88
    ategori
    0.87
     に
    0.85
    peu
    0.84
     lit
    0.82
    entery
    0.82
    Activations Density 0.000%

    No Known Activations