© 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. 10-GEMMASCOPE-RES-131K
    7. 13472
    Prev
    Next
    INDEX
    Explanations

    legal or citation terms

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

    This neuron primarily detects numeric tokens (numbers, including digits, decimals, and numeric sequences).

    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
    🎀
    -1.22
    {
    -1.22
    塞
    -1.21
    😖
    -1.21
     zdan
    -1.21
    дые
    -1.21
    😺
    -1.20
    Dawg
    -1.20
    logía
    -1.19
     it
    -1.17
    POSITIVE LOGITS
    ↵
    1.57
    最悪
    1.40
    接下來
    1.35
    お土産
    1.35
    However
    1.34
    同じく
    1.31
    Furthermore
    1.29
    こいつ
    1.27
    どっち
    1.27
    Here
    1.26
    Activations Density 0.017%

    No Known Activations