© 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. 70125
    Prev
    Next
    INDEX
    Explanations

    past dates

    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
     sonido
    -1.00
    actually
    -0.98
    哪怕
    -0.93
     Celebrating
    -0.88
     οπο
    -0.86
     so
    -0.85
    ertia
    -0.83
     utbild
    -0.83
    :][
    -0.82
    still
    -0.82
    POSITIVE LOGITS
     before
    1.50
     precedente
    1.06
     preceding
    0.97
     trước
    0.95
     Sebelum
    0.94
    ainte
    0.89
     while
    0.89
     sebelum
    0.88
    وفر
    0.87
     other
    0.86
    Activations Density 0.018%

    No Known Activations