© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31047
    Prev
    Next
    INDEX
    Explanations

    patent numbers and identifiers

    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
     мѣ
    -0.99
     escultura
    -0.93
     Enkel
    -0.91
    illante
    -0.90
     некото
    -0.90
    ingang
    -0.88
     épa
    -0.85
    ítimo
    -0.84
    Geplaatst
    -0.81
    Auch
    -0.80
    POSITIVE LOGITS
     patent
    1.55
     patents
    1.54
     invention
    1.35
     Patent
    1.30
    patent
    1.27
    Patent
    1.25
     Patents
    1.21
     filed
    1.10
     disclosure
    1.05
     issued
    0.99
    Activations Density 0.076%

    No Known Activations