© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107689
    Prev
    Next
    INDEX
    Explanations

    dequeue reusable cell

    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
     المص
    -0.74
    Ả
    -0.73
     Stakeholders
    -0.71
    🚣
    -0.70
    riu
    -0.69
    Mitchell
    -0.68
    fontaine
    -0.68
    よろしくお願い
    -0.68
    Tal
    -0.68
    öbb
    -0.67
    POSITIVE LOGITS
     documentary
    0.84
     質
    0.81
     enemy
    0.74
     sling
    0.73
    lifier
    0.72
     coord
    0.71
    Bordeaux
    0.71
    FULLY
    0.71
    ABILIDAD
    0.71
     Documentary
    0.70
    Activations Density 0.024%

    No Known Activations