© 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. 87208
    Prev
    Next
    INDEX
    Explanations

    numbers before slash

    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
    unyi
    -0.78
     Akk
    -0.78
     relevantes
    -0.74
    unak
    -0.73
     термина
    -0.73
    wikidata
    -0.73
     rightful
    -0.71
    肩
    -0.71
     if
    -0.70
    ilak
    -0.70
    POSITIVE LOGITS
    readAll
    0.89
    zungs
    0.81
     Administrator
    0.79
    يند
    0.77
    drawSprites
    0.77
     comte
    0.77
     média
    0.77
    instead
    0.77
    ἀ
    0.75
     Microsoft
    0.75
    Activations Density 0.008%

    No Known Activations