© 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. 22-GEMMASCOPE-RES-131K
    7. 27158
    Prev
    Next
    INDEX
    Explanations

    groups of people or things

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

    This neuron fires on plural nouns naming countable groups or items (e.g. “members,” “patients,” “schools,” “cases”) often used as subjects or units in quantitative descriptions.

    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
     long
    -1.14
     particularly
    -1.09
     then
    -1.08
     especially
    -1.05
     now
    -1.01
     not
    -1.00
     with
    -0.98
     difficult
    -0.98
     huge
    -0.96
     getting
    -0.93
    POSITIVE LOGITS
     numbering
    1.37
     galore
    1.27
    óricos
    1.13
     goû
    1.13
     רבים
    1.13
     mystérie
    1.11
     redé
    1.08
     تعداد
    1.06
     relâche
    1.05
    fragt
    1.05
    Activations Density 0.195%

    No Known Activations