© 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. 34-GEMMASCOPE-RES-131K
    7. 7187
    Prev
    Next
    INDEX
    Explanations

    exception messages or names

    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_34/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
     auxiliary
    -0.76
    モス
    -0.75
    мя
    -0.75
     بعد
    -0.75
    meia
    -0.73
    ](
    -0.73
     Eigentü
    -0.73
    żer
    -0.72
     але
    -0.72
    anello
    -0.71
    POSITIVE LOGITS
     previous
    1.11
     initWithFrame
    0.85
    getMessage
    0.83
    Previous
    0.82
    essage
    0.79
     koje
    0.78
     Pretty
    0.78
    getCode
    0.77
    regulations
    0.74
    ->__
    0.73
    Activations Density 0.011%

    No Known Activations