© 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. 22-GEMMASCOPE-RES-131K
    7. 13297
    Prev
    Next
    INDEX
    Explanations

    the more, the

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects iterative comparative constructions, especially the correlative “the more … the more …” pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    mainly
    -1.32
    possibly
    -1.27
     molto
    -1.27
    €”
    -1.25
     trois
    -1.23
    probably
    -1.21
     garan
    -1.20
    一丝
    -1.19
     tristes
    -1.18
    ention
    -1.17
    POSITIVE LOGITS
     you
    2.59
     we
    1.91
     your
    1.64
     it
    1.56
     they
    1.46
    After
    1.42
     people
    1.37
     I
    1.34
    While
    1.33
    For
    1.25
    Activations Density 0.006%

    No Known Activations