© 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. 63327
    Prev
    Next
    INDEX
    Explanations

    margin and padding

    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
     frot
    -1.01
     parlement
    -0.94
     Caracter
    -0.90
    ✣
    -0.89
     loup
    -0.89
     GERMANY
    -0.88
    Lø
    -0.87
     Regions
    -0.87
    johtaja
    -0.86
    Subtype
    -0.86
    POSITIVE LOGITS
     MAR
    0.89
     Mar
    0.84
    Mar
    0.83
     margin
    0.81
     inneces
    0.79
     glimpse
    0.75
     plus
    0.75
     design
    0.75
    di
    0.75
    MAR
    0.73
    Activations Density 0.007%

    No Known Activations