© 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. 45493
    Prev
    Next
    INDEX
    Explanations

    activities and actions

    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
     from
    -0.91
     riguarda
    -0.87
    avedra
    -0.87
    لح
    -0.83
     xứ
    -0.81
    textTheme
    -0.81
    izarse
    -0.80
     saranno
    -0.80
    nextProps
    -0.80
     approached
    -0.77
    POSITIVE LOGITS
     eat
    1.74
     playing
    1.74
     attend
    1.68
     visit
    1.55
     play
    1.51
     watch
    1.48
     watching
    1.46
     eating
    1.45
     shopping
    1.45
     pergi
    1.45
    Activations Density 0.057%

    No Known Activations