© 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. 71119
    Prev
    Next
    INDEX
    Explanations

    C# code structure

    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
     angebra
    -1.59
     to
    -1.59
    </em>
    -1.38
    
    -1.37
     suitably
    -1.36
    ônico
    -1.34
    ۲۰
    -1.31
    ⢪
    -1.29
    …”
    -1.29
     erwor
    -1.28
    POSITIVE LOGITS
     and
    1.48
    larla
    1.41
    ávat
    1.40
    辇
    1.36
    鍗
    1.30
    ”？
    1.30
    呖
    1.30
     אחרים
    1.30
     olyan
    1.29
    лте
    1.29
    Activations Density 0.022%

    No Known Activations