© 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. 100973
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions

    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
     What
    -2.56
     epitom
    -2.38
     for
    -2.30
     Also
    -2.28
     boasts
    -2.25
     longstanding
    -2.25
     just
    -2.23
            
    -2.23
     encompasses
    -2.22
     undeniably
    -2.22
    POSITIVE LOGITS
     is
    3.09
    沵
    2.72
    虓
    2.59
    *"
    2.50
     vile
    2.44
     convain
    2.42
    艄
    2.39
    every
    2.39
    ˜
    2.27
     serene
    2.23
    Activations Density 0.007%

    No Known Activations