© 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. 23536
    Prev
    Next
    INDEX
    Explanations

    number strings following symbols

    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
    currentColor
    -1.16
    bigr
    -1.05
    淠
    -1.04
     viewWillAppear
    -1.01
     himmel
    -1.01
     higien
    -0.99
     gese
    -0.98
     gela
    -0.95
    гам
    -0.94
     robuste
    -0.94
    POSITIVE LOGITS
     puffer
    0.89
     ordinate
    0.88
     xer
    0.83
     zowel
    0.82
     aptly
    0.80
     meteen
    0.79
     Aggressive
    0.79
     unterstützen
    0.77
     אינו
    0.77
    どちら
    0.75
    Activations Density 0.001%

    No Known Activations