© 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. 73639
    Prev
    Next
    INDEX
    Explanations

    Genre, Tag, or prefixes

    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
     radikal
    -0.87
    ICR
    -0.85
     roj
    -0.77
     dels
    -0.76
     aix
    -0.75
     izin
    -0.75
    ">"
    -0.75
    mässig
    -0.74
     Brigade
    -0.74
     фигур
    -0.73
    POSITIVE LOGITS
     versteht
    0.88
     pós
    0.80
    zeň
    0.79
    之意
    0.77
    єн
    0.75
     Postal
    0.75
     sendMessage
    0.74
    uttering
    0.74
    byshev
    0.73
    忒
    0.73
    Activations Density 0.000%

    No Known Activations