© 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. 58093
    Prev
    Next
    INDEX
    Explanations

    conditional formatting and styling

    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
    medad
    -0.84
    ytu
    -0.83
    glGen
    -0.82
    setImageResource
    -0.79
    MaxValue
    -0.76
    GoogleApiClient
    -0.75
     ślub
    -0.73
    取
    -0.71
    centralwidget
    -0.71
     chipping
    -0.71
    POSITIVE LOGITS
     formatting
    4.06
    formatting
    2.86
     Formatting
    2.86
     styling
    2.72
     format
    2.66
    Formatting
    2.58
     formatted
    2.34
     style
    2.27
    format
    2.20
     Format
    2.13
    Activations Density 0.198%

    No Known Activations