© 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. 87261
    Prev
    Next
    INDEX
    Explanations

    list items and section headings

    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
     firft
    -1.17
     هذه
    -0.98
     tersebut
    -0.98
     لهذه
    -0.97
     thofe
    -0.96
    sprechen
    -0.93
     francia
    -0.93
     této
    -0.92
     byli
    -0.91
     pazar
    -0.91
    POSITIVE LOGITS
     if
    1.57
    1.27
     If
    1.24
    item
    1.13
     $
    1.13
    1.11
    [
    1.11
     There
    1.06
     [
    1.04
     $\
    1.04
    Activations Density 0.020%
    No Known Activations