© 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. 101853
    Prev
    Next
    INDEX
    Explanations

    Test and ODI matches

    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
    ᠁
    -2.14
     gebruiken
    -1.98
    穑
    -1.95
     first
    -1.88
     ráp
    -1.79
    
    -1.76
    
    -1.73
    鹇
    -1.70
    雠
    -1.69
    螃
    -1.63
    POSITIVE LOGITS
     there
    1.78
     from
    1.73
    If
    1.66
    During
    1.64
    Since
    1.63
     when
    1.61
     during
    1.56
     where
    1.54
    i
    1.52
     it
    1.51
    Activations Density 0.012%

    No Known Activations