© 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. 37995
    Prev
    Next
    INDEX
    Explanations

    code comments and metadata

    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
    sequence
    -0.86
    CreateDate
    -0.75
    location
    -0.73
    ską
    -0.69
     молока
    -0.68
     PDO
    -0.67
    ūsu
    -0.65
     sequence
    -0.65
     Wiss
    -0.65
    PDO
    -0.64
    POSITIVE LOGITS
    idd
    0.73
    chaffung
    0.72
    jured
    0.70
    要把
    0.70
     aynı
    0.68
     dull
    0.68
     announced
    0.67
    zecz
    0.66
     Finanzierung
    0.66
     gesetzt
    0.65
    Activations Density 0.052%

    No Known Activations