© 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. 35248
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

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

    The neuron fires on numerical literal tokens—especially the digits and decimal points that make up floating‐point 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
    醍
    -1.52
    を
    -1.52
    もしろ
    -1.47
    もちゃ
    -1.39
    <bos>
    -1.37
    などが
    -1.34
     in
    -1.32
     lebih
    -1.28
    方針
    -1.28
    態度
    -1.25
    POSITIVE LOGITS
    為に
    1.90
    ところに
    1.46
    に入れる
    1.45
    に入れ
    1.43
    感じで
    1.39
    すっ
    1.37
     venerdì
    1.34
    を探す
    1.30
    あー
    1.29
    の絵
    1.29
    Activations Density 0.017%

    No Known Activations