© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30656
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by form of 'be'

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

    The neuron activates on English modal auxiliary verbs (words that express possibility, permission, obligation, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     WERE
    -1.31
     Were
    -1.13
    Were
    -1.11
     make
    -1.10
    她就
    -1.07
     gave
    -0.99
     didnt
    -0.99
     took
    -0.94
     dolay
    -0.94
    BEC
    -0.93
    POSITIVE LOGITS
     be
    3.44
     được
    3.17
     being
    2.63
     быть
    2.59
    被
    2.45
     être
    2.38
     бути
    2.34
     been
    2.27
     essere
    2.19
     být
    2.02
    Activations Density 0.184%

    No Known Activations