© 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. 34-GEMMASCOPE-RES-131K
    7. 45615
    Prev
    Next
    INDEX
    Explanations

    designing and developing with purpose

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

    The neuron flags past-participial verbs (and similar “-ed” forms) used to describe how something is designed, equipped, developed, built, 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
     rebajas
    -1.02
    をご覧ください
    -1.00
     hermosas
    -0.99
     decorativas
    -0.98
    babkan
    -0.98
     étan
    -0.97
    ߳
    -0.96
     botines
    -0.96
     nutzt
    -0.96
     decorativos
    -0.95
    POSITIVE LOGITS
     keeping
    2.84
     considering
    2.45
     according
    2.28
     Keeping
    2.16
    keeping
    2.11
    Keeping
    2.09
    considering
    1.88
     to
    1.80
     with
    1.71
     Considering
    1.70
    Activations Density 0.036%

    No Known Activations