© 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. 119124
    Prev
    Next
    INDEX
    Explanations

    URL links and applications

    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
    Accessible
    -0.83
     Accessible
    -0.79
     przyzna
    -0.76
     jobber
    -0.73
     Emo
    -0.73
     gauze
    -0.71
     climbers
    -0.70
    aksikan
    -0.69
     electrode
    -0.68
    chien
    -0.68
    POSITIVE LOGITS
     deep
    1.91
     Deep
    1.62
    deep
    1.61
    Deep
    1.54
     URI
    1.48
     url
    1.42
     URL
    1.31
     URLs
    1.30
     link
    1.30
     scheme
    1.26
    Activations Density 0.076%

    No Known Activations