© 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. 67733
    Prev
    Next
    INDEX
    Explanations

    portion, amount, quantity

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

    The neuron fires on words that describe size or quantity—especially portion‐ or amount‐related descriptors (e.g. “heaped,” “plate,” “sized,” “portions,” “huge,” “pieces”).

    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
     in
    -1.41
     through
    -1.30
    vedo
    -1.15
     on
    -1.12
     الوزراء
    -1.09
    ATIVES
    -1.00
     无
    -0.99
    āk
    -0.95
     new
    -0.94
     knew
    -0.94
    POSITIVE LOGITS
     verres
    1.29
     testamento
    1.26
     generous
    1.23
     quantity
    1.16
     tiroirs
    1.15
    しゃれ
    1.14
    VERY
    1.14
     témoins
    1.14
    Ħ
    1.12
    もしろ
    1.11
    Activations Density 0.006%

    No Known Activations