© 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. 23742
    Prev
    Next
    INDEX
    Explanations

    Manny Puig, Yoon Seung-ah, Buddhist texts

    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
    kär
    -0.82
     Virgen
    -0.79
     TSH
    -0.77
     Amour
    -0.72
     Deus
    -0.71
     spiced
    -0.69
     Lateral
    -0.69
     Богу
    -0.69
    parer
    -0.69
     Tsch
    -0.69
    POSITIVE LOGITS
    charCode
    0.86
     Pagoda
    0.82
     Burmese
    0.82
     Vip
    0.79
     Pali
    0.76
    $_(
    0.76
     Dha
    0.75
    Vip
    0.75
    יתי
    0.73
    Pall
    0.73
    Activations Density 0.032%

    No Known Activations