© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129479
    Prev
    Next
    INDEX
    Explanations

    future occurrences

    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
    \
    -1.91
     that
    -1.91
     why
    -1.84
    metido
    -1.66
    
    -1.64
     nécessité
    -1.55
     you
    -1.53
    咴
    -1.48
     diferencial
    -1.47
    
    -1.46
    POSITIVE LOGITS
    :"
    1.66
    )"
    1.66
    或是
    1.63
    详细
    1.62
     industrie
    1.59
    旆
    1.57
    ,"
    1.55
    legte
    1.49
    _{
    1.47
    …！
    1.45
    Activations Density 0.011%

    No Known Activations