© 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. 10-GEMMASCOPE-RES-131K
    7. 85067
    Prev
    Next
    INDEX
    Explanations

    code and structured text

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

    The neuron fires on numeric literals (numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    <bos>
    -1.63
    ,
    -1.57
     ANCHE
    -1.56
     estadounidense
    -1.51
     américain
    -1.45
    ܖ
    -1.45
    妧
    -1.44
    姆
    -1.43
    орты
    -1.41
     Barcelone
    -1.41
    POSITIVE LOGITS
    ).
    1.88
     можно
    1.44
     quando
    1.37
     kms
    1.34
    全都
    1.27
    完了
    1.25
    可以直接
    1.24
    jaqueta
    1.24
    ocity
    1.20
    satunya
    1.20
    Activations Density 0.019%

    No Known Activations