© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34372
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    The neuron activates whenever it sees numeric tokens or digits (e.g. equation numbers, exponents, “0”, “2”, “3”, etc.) in mathematical formulas.

    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
    為に
    -2.05
    際に
    -1.62
    ところに
    -1.57
    ことも
    -1.55
    様な
    -1.48
    こともあり
    -1.47
    ために
    -1.43
    に入れる
    -1.41
    ためには
    -1.38
    に入れ
    -1.38
    POSITIVE LOGITS
    <0xA3>
    1.49
    <bos>
    1.42
    そして
    1.41
    礎
    1.41
    そうですね
    1.40
    ？』
    1.38
    がありますが
    1.38
    Since
    1.35
    jangkau
    1.35
     createSprite
    1.32
    Activations Density 0.007%

    No Known Activations