© 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. 86972
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    ristorante
    -0.85
     クーポン
    -0.80
    verez
    -0.79
     herida
    -0.77
    Revert
    -0.76
     Preferences
    -0.76
     poł
    -0.75
     pomp
    -0.75
    Lịch
    -0.75
    posto
    -0.75
    POSITIVE LOGITS
    実際の
    0.81
     ($("#
    0.77
    ственную
    0.74
    cj
    0.74
    andering
    0.73
     Eb
    0.73
    Ers
    0.72
    eaux
    0.71
     regering
    0.71
    :[
    0.70
    Activations Density 0.045%

    No Known Activations