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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47954
    Prev
    Next
    INDEX
    Explanations

    before an action

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

    This neuron detects expressions of ability or potential, especially the modal “could” and words like “able.”

    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
    Other
    -1.25
     químicos
    -1.25
    ició
    -1.23
    Would
    -1.15
    Starting
    -1.13
    Very
    -1.12
     ilyen
    -1.10
    It
    -1.09
    Really
    -1.09
    そのため
    -1.07
    POSITIVE LOGITS
     then
    2.41
     interieur
    1.58
     majest
    1.41
     sitten
    1.40
     than
    1.40
     dezelve
    1.39
     navegador
    1.38
     about
    1.36
     suave
    1.33
     they
    1.32
    Activations Density 0.017%

    No Known Activations