© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84630
    Prev
    Next
    INDEX
    Explanations

    each and every one

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

    The neuron strongly activates on emphatic universal quantifier phrases—most notably “each and every (one)” and similar “every single” constructions.

    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
     for
    -1.78
    Some
    -1.63
    某些
    -1.63
     Schlafzimmer
    -1.59
     Providing
    -1.58
    鏨
    -1.52
     escribiendo
    -1.52
     Wohnzimmer
    -1.48
     only
    -1.47
     really
    -1.47
    POSITIVE LOGITS
     those
    1.61
     praktische
    1.47
     spille
    1.46
     that
    1.43
     you
    1.41
    StoryboardSegue
    1.41
     it
    1.41
    ometry
    1.38
    も見
    1.38
     them
    1.37
    Activations Density 0.010%

    No Known Activations