© 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. 86639
    Prev
    Next
    INDEX
    Explanations

    messenger RNA and institutions

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

    The neuron fires on formal institutional or organizational nouns and titles (e.g. Commission, Convention, Seminary, Synod, Trustees).

    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
    DOES
    -1.48
     autorisé
    -1.39
    ❖
    -1.38
     afectados
    -1.37
    BUT
    -1.36
    VERY
    -1.35
     guapos
    -1.35
     preparados
    -1.33
    明显的
    -1.33
    ☐
    -1.31
    POSITIVE LOGITS
    ouchers
    1.68
    hydrogenase
    1.64
    oluzione
    1.64
    aussian
    1.61
     why
    1.60
    itivo
    1.60
    ngine
    1.59
    GIVEREF
    1.57
     gdyż
    1.57
     zrobić
    1.55
    Activations Density 0.011%

    No Known Activations