© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93886
    Prev
    Next
    INDEX
    Explanations

    Bootstrap and CSS framework

    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
     årene
    -0.82
    らず
    -0.80
    бва
    -0.78
     überrascht
    -0.76
     auxiliar
    -0.75
     flamen
    -0.75
    频
    -0.75
     piedras
    -0.75
     strikeouts
    -0.75
     kjent
    -0.74
    POSITIVE LOGITS
     BOOT
    0.93
    bootstrapcdn
    0.83
     Veronica
    0.83
    DeclareMath
    0.82
    ༒
    0.81
     concurso
    0.78
    Jau
    0.75
     balk
    0.75
    τως
    0.73
     gà
    0.73
    Activations Density 0.002%

    No Known Activations