© 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. 75810
    Prev
    Next
    INDEX
    Explanations

    Obama

    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
     kla
    -0.91
    닝
    -0.91
     comprendre
    -0.90
    TING
    -0.89
     oyunu
    -0.88
    irait
    -0.87
    assing
    -0.87
     aile
    -0.86
     escla
    -0.85
    izadas
    -0.85
    POSITIVE LOGITS
     if
    1.03
    ።
    0.78
     If
    0.78
    pedro
    0.78
     within
    0.77
     meticulous
    0.75
     very
    0.75
     wish
    0.74
    手間
    0.74
     any
    0.73
    Activations Density 0.001%

    No Known Activations