© 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. 84134
    Prev
    Next
    INDEX
    Explanations

    book descriptions

    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
     endangered
    -0.75
     Aufenthalt
    -0.74
     hospitalization
    -0.74
    즐
    -0.73
    président
    -0.71
    piercing
    -0.71
     derselben
    -0.71
    oflavin
    -0.71
    ώ
    -0.70
    operatorname
    -0.69
    POSITIVE LOGITS
     blanks
    0.85
    Blank
    0.84
     blank
    0.84
     sexuelle
    0.78
     romantique
    0.74
    ColumnIndex
    0.73
     厂
    0.73
     непре
    0.72
     arabe
    0.72
     جدا
    0.72
    Activations Density 0.020%

    No Known Activations