© 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. 34-GEMMASCOPE-RES-131K
    4. 60841
    Prev
    Next
    INDEX
    Explanations

    FILED court documents

    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
     supremely
    -2.25
     ostensibly
    -2.17
     when
    -2.17
     blatantly
    -2.13
     markedly
    -2.09
     this
    -2.09
     epitom
    -2.08
     began
    -2.06
     unrelenting
    -2.03
     furthering
    -2.00
    POSITIVE LOGITS
     !!!!
    1.92
     dando
    1.88
     myriad
    1.86
     horrid
    1.84
     luscious
    1.83
     quirky
    1.81
     whimsical
    1.80
     shimmering
    1.80
     sumptuous
    1.77
     delightfully
    1.77
    Activations Density 0.013%

    No Known Activations