© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14217
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and dates

    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
    まるで
    -1.10
     cykel
    -1.04
    妧
    -1.02
     Merah
    -1.02
     kilomet
    -1.02
     թվական
    -1.02
    他又
    -1.01
     kuj
    -1.00
    こちらも
    -0.99
     trafik
    -0.98
    POSITIVE LOGITS
     原因
    1.00
     Schulen
    0.98
     {},
    0.95
    endetta
    0.92
    
    0.91
    ญี่ปุ่น
    0.91
     Однако
    0.90
    ónima
    0.90
     depending
    0.88
    ಃ
    0.88
    Activations Density 0.082%

    No Known Activations