© 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. 22-GEMMASCOPE-RES-131K
    7. 67105
    Prev
    Next
    INDEX
    Explanations

    of America

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

    The neuron consistently activates on the preposition “of.”

    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
     already
    -0.96
     permisos
    -0.91
     requirement
    -0.91
    Derp
    -0.89
     hoteles
    -0.87
     «<
    -0.86
     mensaj
    -0.85
     memasak
    -0.85
    chien
    -0.85
     entretenimiento
    -0.85
    POSITIVE LOGITS
    Πηγές
    1.02
    ando
    0.97
    ्म
    0.94
    륭
    0.94
    唰
    0.91
     bénéficient
    0.90
     ingen
    0.89
    ума
    0.89
     dignité
    0.88
    噗
    0.88
    Activations Density 0.001%

    No Known Activations