© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68952
    Prev
    Next
    INDEX
    Explanations

    counting items or numbers

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

    The neuron fires on generalizing/quantifier words (e.g. “some,” “each,” “all,” “one,” “most,” etc.).

    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
     ones
    -1.94
     которых
    -1.80
    They
    -1.50
     them
    -1.44
     mereka
    -1.41
    Ones
    -1.41
     onları
    -1.41
     denen
    -1.31
     которые
    -1.30
     they
    -1.28
    POSITIVE LOGITS
     its
    3.39
     it
    2.16
    它的
    1.87
     فيه
    1.52
     Its
    1.45
    Its
    1.41
     فيها
    1.34
     её
    1.33
    把它
    1.31
     ее
    1.30
    Activations Density 0.190%

    No Known Activations