© 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. 19797
    Prev
    Next
    INDEX
    Explanations

    so-called, ever, remembers

    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
     of
    -2.69
     but
    -1.73
     dlatego
    -1.60
     gdyby
    -1.54
     would
    -1.46
    㐂
    -1.41
     Tetapi
    -1.35
     must
    -1.34
    }%
    
    -1.33
     Semoga
    -1.33
    POSITIVE LOGITS
    躥
    1.44
     mortos
    1.43
    📎
    1.36
     élev
    1.35
    を搭載
    1.30
    剉
    1.30
     toilettes
    1.30
    🔷
    1.29
     soirée
    1.27
     lunettes
    1.25
    Activations Density 0.186%

    No Known Activations