© 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. 22-GEMMASCOPE-RES-131K
    4. 35808
    Prev
    Next
    INDEX
    Explanations

    works fine or great

    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_22/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
     хотя
    -0.93
    ienė
    -0.92
    baugh
    -0.91
     quelconque
    -0.90
     zamiast
    -0.90
    ും
    -0.88
    rana
    -0.86
     både
    -0.86
     ouverts
    -0.84
    any
    -0.82
    POSITIVE LOGITS
     but
    2.06
     until
    1.50
     for
    1.43
     when
    1.41
     ولكن
    1.38
    但是
    1.18
     nhưng
    1.11
    But
    1.09
     BUT
    1.07
     But
    1.05
    Activations Density 0.160%

    No Known Activations