© 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. 90843
    Prev
    Next
    INDEX
    Explanations

    Mei, Mayweather, Meier, McAvoy

    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
    so
    -3.27
     видит
    -2.94
    be
    -2.86
    sø
    -2.73
     получает
    -2.64
    ter
    -2.61
    激烈
    -2.55
    تیجه
    -2.55
     så
    -2.53
     assess
    -2.45
    POSITIVE LOGITS
    ⟣
    2.72
    The
    2.56
    鲥
    2.53
    考虑到
    2.50
    葙
    2.44
    楽しめる
    2.44
            
    2.44
     ใน
    2.39
    来到了
    2.36
     chrétien
    2.36
    Activations Density 0.002%

    No Known Activations