© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12717
    Prev
    Next
    INDEX
    Explanations

    actions to ensure or determine

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

    The neuron strongly activates on the function word “to.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     flott
    -1.11
     diinginkan
    -1.09
    TRAVIS
    -1.08
     bottes
    -1.07
    ؋
    -1.06
     moulin
    -1.05
     inapropiados
    -1.04
     pouces
    -1.02
     againſt
    -1.02
    specie
    -1.02
    POSITIVE LOGITS
     how
    1.86
     whether
    1.79
     determine
    1.59
     if
    1.53
     understand
    1.52
     know
    1.52
     see
    1.38
     ensure
    1.38
     decide
    1.38
     případ
    1.22
    Activations Density 0.042%

    No Known Activations