© 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. 31400
    Prev
    Next
    INDEX
    Explanations

    highlighting and enhancing visibility

    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
     Sortiment
    -0.86
     indicadores
    -0.82
    отно
    -0.82
     estética
    -0.82
    ススメ
    -0.79
     يعد
    -0.77
    ンク
    -0.76
     inspiri
    -0.76
     inspires
    -0.75
     explicado
    -0.75
    POSITIVE LOGITS
     highlight
    2.59
     highlighting
    2.50
    highlight
    2.47
    Highlight
    2.42
     highlights
    2.31
     подчер
    2.17
     Highlight
    2.14
     highlighted
    2.06
     accentu
    2.03
     showcase
    2.02
    Activations Density 0.060%

    No Known Activations