© 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. 10-GEMMASCOPE-RES-131K
    7. 102482
    Prev
    Next
    INDEX
    Explanations

    conditionals about ability

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

    The neuron is primarily activated by occurrences of the modal verb “can.”

    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
    nearly
    -1.61
    )$
    -1.49
     presque
    -1.41
     hashCode
    -1.36
    噙
    -1.33
    惋
    -1.31
    鶿
    -1.30
     cirka
    -1.30
    
    -1.27
     connus
    -1.26
    POSITIVE LOGITS
     work
    1.38
     based
    1.27
     will
    1.24
     میشود
    1.22
     one
    1.22
    عمال
    1.16
     provide
    1.16
     Currently
    1.16
     aufgrund
    1.14
     Despite
    1.13
    Activations Density 0.056%

    No Known Activations