© 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. 22-GEMMASCOPE-RES-131K
    4. 12815
    Prev
    Next
    INDEX
    Explanations

    another, other, new

    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_22/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
    。  
    -0.94
    かう
    -0.87
     cero
    -0.87
    などなど
    -0.86
     ブランド
    -0.85
     Grüßen
    -0.84
     projet
    -0.83
     golf
    -0.83
     Golf
    -0.81
     середи
    -0.81
    POSITIVE LOGITS
     another
    1.52
     other
    1.20
    Another
    1.08
     next
    1.05
     دیگری
    1.04
     další
    1.02
    another
    0.95
     másik
    0.93
    อีก
    0.92
     dalších
    0.91
    Activations Density 0.008%

    No Known Activations