© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128578
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on plural nouns (i.e. words ending in “s”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    discrete entities or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    หรือ
    -1.02
    वेश
    -0.99
     two
    -0.97
    awtextra
    -0.93
     metody
    -0.92
    や
    -0.91
     トラベル
    -0.91
     主
    -0.91
    开学
    -0.91
    siye
    -0.90
    POSITIVE LOGITS
     that
    1.34
    ất
    1.12
    舆
    1.07
    ambahkan
    1.03
    northeast
    1.01
    瞟
    1.00
    zaine
    0.99
     miteinander
    0.98
    āciju
    0.98
    着脸
    0.96
    Activations Density 0.141%

    No Known Activations