© 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. 22-GEMMASCOPE-RES-131K
    7. 79971
    Prev
    Next
    INDEX
    Explanations

    founding or starting new entities

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

    The neuron responds to verbs that denote founding, establishing, or creating organizations or institutions.

    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
     they
    -1.23
     poiché
    -1.15
    來的
    -1.13
     éstos
    -1.13
     każdy
    -1.10
    though
    -1.09
    potentially
    -1.09
     results
    -1.07
     wszystkie
    -1.05
     cuyas
    -1.05
    POSITIVE LOGITS
     a
    2.45
     an
    1.98
     new
    1.56
     our
    1.38
     একটি
    1.33
     sebuah
    1.26
     one
    1.23
    гите
    1.20
     marvellous
    1.17
     in
    1.16
    Activations Density 0.053%

    No Known Activations