© 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. 8410
    Prev
    Next
    INDEX
    Explanations

    mathematical quantifiers and contexts

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

    This neuron activates on occurrences of the universal quantifier "forall."

    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
    茕
    -2.83
    푣
    -2.47
    畬
    -2.25
     \"
    -2.20
    ſam
    -2.17
    让你
    -2.14
    i
    -2.11
     famosas
    -2.11
    댔
    -2.11
     تھے
    -2.08
    POSITIVE LOGITS
     There
    2.67
     Everyone
    2.67
     Someone
    2.64
     Anyone
    2.59
     Thousands
    2.50
     Another
    2.41
     Especially
    2.41
     Selecting
    2.34
     Thanks
    2.34
     Acknowled
    2.28
    Activations Density 0.004%

    No Known Activations