© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66180
    Prev
    Next
    INDEX
    Explanations

    will be; will + verb

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

    The neuron primarily detects the modal auxiliary “will,” marking future‐tense constructions.

    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
    .
    -1.59
     puis
    -1.34
     ridd
    -1.34
     parfois
    -1.33
    beca
    -1.28
    GIVE
    -1.28
    भु
    -1.28
     zon
    -1.27
     płasz
    -1.26
     THOUS
    -1.25
    POSITIVE LOGITS
     two
    1.74
     three
    1.60
     and
    1.58
     from
    1.55
    Two
    1.55
     had
    1.55
     Two
    1.54
     Several
    1.49
     with
    1.46
     will
    1.45
    Activations Density 0.057%

    No Known Activations