© 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. 1386
    Prev
    Next
    INDEX
    Explanations

    stock tickers and exchanges

    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
     for
    -1.97
     after
    -1.92
     at
    -1.77
     on
    -1.76
     I
    -1.75
     from
    -1.66
     this
    -1.65
    !
    -1.64
    ).
    -1.64
     both
    -1.61
    POSITIVE LOGITS
    푉
    1.66
     ſever
    1.56
    ᡴ
    1.52
    
    1.48
    wouldn
    1.48
     jednou
    1.44
    
    1.43
    ſtre
    1.42
     incendios
    1.41
    Île
    1.41
    Activations Density 0.244%

    No Known Activations