© 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. 70023
    Prev
    Next
    INDEX
    Explanations

    programming keywords and punctuation

    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
    omburg
    -0.75
     ју
    -0.69
     does
    -0.69
    zī
    -0.68
    Does
    -0.65
    挛
    -0.64
     Dany
    -0.64
     riveting
    -0.62
    ccio
    -0.62
     without
    -0.61
    POSITIVE LOGITS
    Cruz
    0.79
     Pip
    0.76
    ________
    0.71
    
    0.71
    Pip
    0.70
    BorderSize
    0.69
    goth
    0.69
    готавли
    0.66
    CompoundButton
    0.66
    driven
    0.66
    Activations Density 0.026%

    No Known Activations