© 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. 75023
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    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
    珦
    -2.45
     honom
    -1.99
    
    -1.91
    providedIn
    -1.91
    鼙
    -1.90
     suure
    -1.87
    jaqueta
    -1.80
    
    -1.78
     शुर
    -1.76
    amerikanischer
    -1.74
    POSITIVE LOGITS
    ↵
    2.73
    ll
    2.38
    to
    2.27
    8
    2.20
     wykorzyst
    1.91
    with
    1.83
    榦
    1.77
    lgari
    1.69
     cualquier
    1.69
     porque
    1.69
    Activations Density 0.001%

    No Known Activations