© 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. 22-GEMMASCOPE-RES-131K
    7. 129900
    Prev
    Next
    INDEX
    Explanations

    The neuron detects modal or auxiliary verbs (like must, have to, need to, can, could, will) indicating necessity, possibility, or futurity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    must, need, should, want, can, could followed by action

    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_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
    為に
    -1.51
    のですね
    -1.47
     tevreden
    -1.41
     inicios
    -1.37
    arashtra
    -1.36
    んですよね
    -1.32
     umożli
    -1.32
     Meksiku
    -1.30
    alisco
    -1.30
     analizar
    -1.30
    POSITIVE LOGITS
     turist
    1.41
     only
    1.38
    掬
    1.23
    囁
    1.20
     hommage
    1.19
     Meksi
    1.19
    という感じ
    1.16
     this
    1.13
     financi
    1.12
    違和
    1.12
    Activations Density 0.049%

    No Known Activations