© 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. 6958
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    檻
    -0.87
     Nineteen
    -0.85
    而来
    -0.79
    意识
    -0.77
    apropri
    -0.74
    pgs
    -0.74
     Daven
    -0.73
    giu
    -0.73
     особо
    -0.70
     Thirty
    -0.69
    POSITIVE LOGITS
    0
    1.02
     forskjellige
    0.93
    5
    0.90
     sisält
    0.85
     všetkých
    0.82
     eikä
    0.81
    Appeal
    0.80
    sqlite
    0.80
     decenas
    0.78
     denken
    0.77
    Activations Density 0.065%

    No Known Activations