© 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. 10-GEMMASCOPE-RES-131K
    4. 90695
    Prev
    Next
    INDEX
    Explanations

    even if / though / when

    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_10/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
     than
    -1.84
     également
    -1.70
     igualmente
    -1.63
     також
    -1.62
     επίσης
    -1.61
     also
    -1.59
     또
    -1.59
     также
    -1.58
     need
    -1.55
     גם
    -1.55
    POSITIVE LOGITS
     when
    2.23
     though
    2.13
     for
    2.13
     because
    2.00
     where
    1.90
    ╣
    1.69
     our
    1.68
     právě
    1.64
    سون
    1.63
     those
    1.63
    Activations Density 0.009%

    No Known Activations