© 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. 27643
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, names, and professional titles

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

    The neuron selectively activates on numeric tokens (digits or numbers) within mathematical expressions.

    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
     hermos
    -1.27
     moſt
    -1.23
     flera
    -1.21
    例文帳に追加
    -1.19
    乄
    -1.18
     trasero
    -1.17
     focussing
    -1.17
     食物
    -1.16
     mehreren
    -1.16
     nutrientes
    -1.16
    POSITIVE LOGITS
    🩹
    1.42
     upacara
    1.21
     with
    1.18
     ujar
    1.16
    Preço
    1.12
    Those
    1.09
     at
    1.09
     There
    1.09
    Karakter
    1.07
    𓂂
    1.07
    Activations Density 0.005%

    No Known Activations