© 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. 84093
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, formulas, and 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_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
     restre
    -0.89
     Pemberton
    -0.88
     eaux
    -0.88
    ⁱ
    -0.84
    そろ
    -0.82
    猫咪
    -0.82
     utan
    -0.81
     تک
    -0.79
     stel
    -0.79
    cible
    -0.79
    POSITIVE LOGITS
     quindi
    0.96
     nuestro
    0.85
    chaleco
    0.83
     Поэтому
    0.83
    állítás
    0.82
    paroles
    0.82
    ◟
    0.81
     två
    0.80
    isburg
    0.80
     blaue
    0.79
    Activations Density 0.006%

    No Known Activations