© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119713
    Prev
    Next
    INDEX
    Explanations

    legal abbreviations and divisions

    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
     stellar
    -2.11
     enormous
    -2.03
     spurred
    -2.00
    leyebilirsiniz
    -1.97
     enticing
    -1.91
     ostensibly
    -1.89
     or
    -1.88
     lancar
    -1.84
     impeccable
    -1.77
     invigor
    -1.77
    POSITIVE LOGITS
     nonchal
    2.22
     revamped
    2.22
     semelh
    2.16
     magnificent
    2.13
     dismal
    2.09
     overly
    2.09
     spectacular
    2.05
     hotly
    2.03
    ..,
    2.03
    を使用した
    1.98
    Activations Density 0.022%

    No Known Activations