© 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. 14754
    Prev
    Next
    INDEX
    Explanations

    technical terms followed by common words

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

    This neuron fires on noun-like words formed with common English derivational suffixes (e.g. –ing, –ion, –ers).

    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
    個人的に
    -1.24
    あぁ
    -1.20
    ほら
    -1.20
    paralleled
    -1.15
     wiedzieć
    -1.14
    wavering
    -1.13
    えっ
    -1.12
    viseur
    -1.11
     beschäf
    -1.10
     traseira
    -1.08
    POSITIVE LOGITS
    詡
    1.26
     in
    1.13
     with
    1.06
    碌
    1.06
    簪
    1.03
     سيكون
    1.02
    hình
    1.01
     his
    1.00
    dtp
    0.99
    篆
    0.99
    Activations Density 0.044%

    No Known Activations