© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102282
    Prev
    Next
    INDEX
    Explanations

    fantasy and science fiction characters

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

    The neuron detects numeric tokens—especially numbers with digits (including decimals).

    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
     its
    -1.60
    cisi
    -1.33
     aperçu
    -1.31
     maniere
    -1.20
    isling
    -1.18
    ٢
    -1.17
     meste
    -1.14
     Domínguez
    -1.14
     coucher
    -1.13
     אותם
    -1.13
    POSITIVE LOGITS
     of
    1.74
    According
    1.34
    一致
    1.31
     According
    1.23
    hoenix
    1.23
     више
    1.19
     nhàng
    1.18
    trà
    1.18
     focused
    1.18
     like
    1.18
    Activations Density 0.008%

    No Known Activations