© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80590
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron strongly activates on numeric tokens (quantities and multi‐digit 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_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
     in
    -1.45
     know
    -1.44
     when
    -1.39
     as
    -1.34
     conscientes
    -1.29
    EMBL
    -1.23
    ティスト
    -1.20
     Roblox
    -1.17
    ➩
    -1.14
     lumin
    -1.13
    POSITIVE LOGITS
    فقط
    1.55
    場所は
    1.54
     มัน
    1.45
    patrón
    1.43
     perdre
    1.41
     Francus
    1.40
     podéis
    1.39
     telah
    1.38
    MfG
    1.37
     rechazo
    1.35
    Activations Density 0.057%

    No Known Activations