© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67514
    Prev
    Next
    INDEX
    Explanations

    all the plurals

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

    The neuron is specifically keyed to detect the 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_22/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
     חיצוניים
    -1.18
    altri
    -1.16
    Vendo
    -1.05
     onSave
    -1.05
    ujuk
    -1.02
    ribue
    -1.02
    
    -1.01
     भी
    -0.99
    enci
    -0.98
    umper
    -0.98
    POSITIVE LOGITS
     possible
    1.63
     of
    1.38
     currently
    1.27
     available
    1.23
    possible
    1.17
     всички
    1.13
     in
    1.09
     viejas
    1.08
     seluruh
    1.07
    Possible
    1.04
    Activations Density 0.062%

    No Known Activations