© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43038
    Prev
    Next
    INDEX
    Explanations

    forming something into existence

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

    The neuron activates specifically on the verb “form.”

    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
    you
    -2.36
    which
    -2.31
    your
    -2.20
    𓋼
    -2.14
    TestingModule
    -2.11
    彞
    -2.06
    that
    -2.06
    婢
    -2.02
    する
    -2.00
     Settembre
    -1.95
    POSITIVE LOGITS
     a
    2.61
    t
    2.38
     unmöglich
    2.13
     könnte
    2.02
     แต่
    2.02
    Hilsen
    1.98
    谖
    1.96
    我对
    1.89
     gewiß
    1.87
     äußerst
    1.85
    Activations Density 0.014%

    No Known Activations