© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103178
    Prev
    Next
    INDEX
    Explanations

    contractions with 'll

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

    The neuron strongly activates on the contraction suffix “’ll” (the “ll” in words like “you’ll,” “he’ll,” “they’ll”), i.e. the contracted form of “will.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     of
    -2.91
     that
    -2.28
     cannot
    -2.22
     so
    -2.17
     these
    -2.16
     when
    -2.13
     which
    -2.09
     this
    -2.05
     it
    -2.02
     even
    -1.98
    POSITIVE LOGITS
    eventually
    2.22
    probably
    2.06
    hopefully
    1.91
    likely
    1.89
     refroid
    1.88
    excellent
    1.85
    jenigen
    1.84
    絝
    1.83
    voer
    1.83
    儈
    1.82
    Activations Density 0.128%

    No Known Activations