© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130458
    Prev
    Next
    INDEX
    Explanations

    holiday and vacation

    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_10/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
    ፑ
    -1.97
    厯
    -1.95
    丷
    -1.93
     reembols
    -1.90
     quiser
    -1.88
     Exteriores
    -1.87
    洨
    -1.85
    
    -1.77
     puder
    -1.76
    
    -1.75
    POSITIVE LOGITS
    g
    2.45
    in
    2.42
    4
    2.16
    ↵↵
    2.14
    e
    2.11
    d
    2.09
    if
    2.08
    3
    2.05
    a
    1.99
    es
    1.98
    Activations Density 0.017%

    No Known Activations