© 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. 111015
    Prev
    Next
    INDEX
    Explanations

    bold or emphasis

    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
    addElement
    -0.80
    ocino
    -0.77
    焼く
    -0.75
    letka
    -0.75
    DELIM
    -0.75
     nepiecieš
    -0.74
    みたら
    -0.73
     its
    -0.71
    ís
    -0.71
    chemy
    -0.71
    POSITIVE LOGITS
     boldly
    0.87
     hôtels
    0.87
    bold
    0.83
     algas
    0.81
    BOLD
    0.79
     bolder
    0.78
    itás
    0.77
     約
    0.76
     bold
    0.76
     Bold
    0.75
    Activations Density 0.009%

    No Known Activations