© 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. 86770
    Prev
    Next
    INDEX
    Explanations

    conjunctions introducing contrast or elaboration

    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
    なので
    -1.77
    ’
    -1.65
    atized
    -1.59
    aning
    -1.55
     tandis
    -1.52
    でも
    -1.52
    vermectin
    -1.49
    carus
    -1.48
    。
    -1.48
    atization
    -1.47
    POSITIVE LOGITS
     or
    2.88
     like
    2.69
     which
    2.64
     along
    2.61
     if
    2.33
     despite
    2.31
     in
    2.30
     from
    2.27
     as
    2.17
     through
    2.14
    Activations Density 0.185%

    No Known Activations