© 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. 44055
    Prev
    Next
    INDEX
    Explanations

    existential quantifiers and limelight

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

    The neuron strongly activates on the word “exists,” i.e. it identifies existential‐quantifier occurrences.

    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
    D
    -3.09
    P
    -3.02
    K
    -2.91
    A
    -2.88
    B
    -2.75
    H
    -2.73
    the
    -2.72
    F
    -2.69
    N
    -2.59
     innumerable
    -2.52
    POSITIVE LOGITS
     traditionelle
    2.45
    鬭
    2.42
     aktive
    2.39
    鷽
    2.38
     笔画
    2.38
     dieß
    2.34
    鵟
    2.30
    酹
    2.28
     vaksin
    2.25
    瞜
    2.25
    Activations Density 0.001%

    No Known Activations