© 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. 129411
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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
     helps
    -2.25
    0
    -2.22
     before
    -2.20
     because
    -2.13
     during
    -2.11
     both
    -2.06
     helping
    -2.05
     what
    -2.05
     where
    -2.02
     undeniably
    -2.00
    POSITIVE LOGITS
     fiasco
    2.00
     estándares
    1.95
     ambiti
    1.94
     soooo
    1.93
     Dinas
    1.87
     !!!!
    1.87
     debacle
    1.83
    those
    1.82
    蚡
    1.81
     ezek
    1.79
    Activations Density 0.010%

    No Known Activations