© 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. 10440
    Prev
    Next
    INDEX
    Explanations

    all of the

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

    The neuron fires on occurrences of the universal-quantifier “all.”

    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
     baterías
    -1.34
     tornillos
    -1.31
     {
    -1.28
    omock
    -1.27
     использование
    -1.27
     tougher
    -1.26
     místě
    -1.22
     neumáticos
    -1.20
    ECB
    -1.19
    kloped
    -1.19
    POSITIVE LOGITS
     even
    1.32
     in
    1.26
     amada
    1.22
     up
    1.18
     Instead
    1.16
     over
    1.05
    kony
    1.00
     the
    1.00
     Completely
    0.98
     даже
    0.98
    Activations Density 0.096%

    No Known Activations