© 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. 10-GEMMASCOPE-RES-131K
    4. 1349
    Prev
    Next
    INDEX
    Explanations

    descriptive nouns following "the" or "this"

    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
    création
    -1.70
    système
    -1.63
    modèle
    -1.63
    pantalón
    -1.58
     there
    -1.54
     sogenannten
    -1.54
    ebly
    -1.53
     those
    -1.49
     belki
    -1.49
     більш
    -1.48
    POSITIVE LOGITS
                
    1.52
     begon
    1.48
     ایم
    1.46
     frites
    1.45
     режим
    1.38
     uruguay
    1.37
     globale
    1.36
    .
    1.35
     geforce
    1.34
             
    1.33
    Activations Density 0.012%

    No Known Activations