© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84782
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

    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
    minY
    -0.87
     Soccerway
    -0.87
     fön
    -0.86
     Unterschied
    -0.85
    ̓
    -0.84
     What
    -0.82
     Gegenstände
    -0.82
    sekret
    -0.82
     phénom
    -0.82
    ことは
    -0.82
    POSITIVE LOGITS
    X
    1.15
     especialmente
    0.98
     Xanth
    0.98
     Xtreme
    0.95
     potre
    0.95
    xPos
    0.92
    xton
    0.91
    xp
    0.90
     inay
    0.90
    特に
    0.89
    Activations Density 0.008%

    No Known Activations