© 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. 93356
    Prev
    Next
    INDEX
    Explanations

    code comments and declarations

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

    The neuron activates on standalone numeric literals (numbers).

    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
     parku
    -1.27
     pán
    -1.27
    AdvEx
    -1.27
     dezelve
    -1.27
     kabát
    -1.27
    ⑊
    -1.26
     trám
    -1.23
    羸
    -1.21
    ଼
    -1.21
     rám
    -1.21
    POSITIVE LOGITS
     also
    1.43
    if
    1.38
     给
    1.26
    ↵↵↵↵↵↵
    1.24
    愜
    1.22
    ちなみに
    1.21
    //
    1.20
    櫚
    1.16
    /**
    1.14
     There
    1.14
    Activations Density 0.017%

    No Known Activations